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

    Neuronpedia

    INDEX
    Explanations

    Code/Programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    latitude
    -0.08
     policeman
    -0.07
     affair
    -0.07
    /****************************************************************
    -0.07
     Zimbabwe
    -0.07
    "x
    -0.07
    Unless
    -0.07
     Service
    -0.07
     dictionary
    -0.07
    departure
    -0.07
    POSITIVE LOGITS
    �
    0.06
     הית
    0.06
     egregious
    0.06
    körper
    0.06
     footing
    0.06
    способ
    0.06
     Fecha
    0.06
     Jacqueline
    0.06
    堐
    0.06
    高地
    0.06
    Act Density 0.213%

    No Known Activations