Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    statistical information related to cells or groups, often within a scientific context

    oai_token-act-pair · gemini-2.0-flash

    scientific terms and entities

    np_token-act-pair-logits · gpt-4o-mini

    scientific comparison

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :✨
    -0.68
     GenerationType
    -0.65
    CodeAttribute
    -0.64
    TintMode
    -0.63
     considérons
    -0.63
    /**
    -0.59
    kháu
    -0.58
    synthesize
    -0.58
    Demografie
    -0.57
    multline
    -0.57
    POSITIVE LOGITS
     فريبيس
    0.49
     sig
    0.45
     species
    0.43
     BorderRadius
    0.43
     GL
    0.42
    Autoritní
    0.42
     caracter
    0.42
     body
    0.40
    ån
    0.39
     DataTypes
    0.39
    Act Density 4.596%

    No Known Activations