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

    Neuronpedia

    INDEX
    Explanations

    words that relate to inventing, manufacturing, or composing something new

    oai_token-act-pair · gemini-2.0-flash

    technical coding or script-related terms

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

    Ingredients/materials

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    værk
    -0.43
     about
    -0.40
    about
    -0.38
    éndole
    -0.38
     
    -0.35
     quali
    -0.35
     Po
    -0.34
     operativos
    -0.34
     å
    -0.34
    šanas
    -0.34
    POSITIVE LOGITS
     ―――――
    0.99
     $_"
    0.98
    contentLoaded
    0.93
    UserScript
    0.91
     Efq
    0.91
     ProtoMessage
    0.90
     myſelf
    0.87
     ――――――――
    0.85
    ."</
    0.83
     tubers
    0.83
    Act Density 9.266%

    No Known Activations