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

    Neuronpedia

    INDEX
    Explanations

    verte

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jong
    -0.07
     Definitions
    -0.07
     originated
    -0.06
    ungalow
    -0.06
    irler
    -0.06
     Laden
    -0.06
    $m
    -0.06
    -making
    -0.06
    heel
    -0.06
     mails
    -0.06
    POSITIVE LOGITS
     prote
    0.07
    ım
    0.07
    tparam
    0.06
    _Code
    0.06
     музы
    0.06
     firebase
    0.06
    wine
    0.06
     verte
    0.06
     groceries
    0.06
     دستی
    0.06
    Act Density 0.001%

    No Known Activations