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

    Neuronpedia

    INDEX
    Explanations

    describing the nature of something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nature
    -0.76
     Савезне
    -0.73
     beginnetje
    -0.69
     lenker
    -0.67
     GenerationType
    -0.66
     natures
    -0.65
     naturaleza
    -0.65
    SourceChecksum
    -0.61
    InputBorder
    -0.61
     ProtoMessage
    -0.61
    POSITIVE LOGITS
    Unchecked
    0.54
     Safely
    0.50
    __*/
    0.50
     safely
    0.50
    definitely
    0.49
     lượt
    0.47
     professional
    0.46
     vaik
    0.46
     zeker
    0.46
     становника
    0.45
    Act Density 0.006%

    No Known Activations