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

    Neuronpedia

    INDEX
    Explanations

    other

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pu
    -0.06
    Locked
    -0.06
    (team
    -0.06
     Detect
    -0.06
     Fet
    -0.06
    WithString
    -0.06
     Café
    -0.06
     belongs
    -0.06
     bec
    -0.06
    strtotime
    -0.06
    POSITIVE LOGITS
     Perl
    0.07
     emlrt
    0.07
     Basically
    0.07
     التر
    0.07
    holding
    0.06
    .NewGuid
    0.06
     структу
    0.06
    InputChange
    0.06
     �
    0.06
    UL
    0.06
    Act Density 0.005%

    No Known Activations