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

    Neuronpedia

    INDEX
    Explanations

    quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cord
    -0.07
     engaging
    -0.07
    .roll
    -0.07
    Old
    -0.06
    inki
    -0.06
     dry
    -0.06
    paragus
    -0.06
    YT
    -0.06
     coffin
    -0.06
     userDetails
    -0.06
    POSITIVE LOGITS
     define
    0.07
    invalid
    0.07
    _attack
    0.06
    _control
    0.06
    客
    0.06
     지금
    0.06
    ционных
    0.06
    ђ
    0.06
     más
    0.06
    	index
    0.06
    Act Density 0.002%

    No Known Activations