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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     올
    -0.06
     nuova
    -0.06
     Mundo
    -0.06
    _MAN
    -0.06
    어진
    -0.06
     soll
    -0.06
     asshole
    -0.06
     flaw
    -0.06
     OD
    -0.06
     sev
    -0.06
    POSITIVE LOGITS
    .Network
    0.07
     Lah
    0.06
     Vegan
    0.06
    /store
    0.06
    caption
    0.06
     Thường
    0.06
    .addHandler
    0.06
    __));↵
    0.06
     masking
    0.06
     Apply
    0.06
    Act Density 0.005%

    No Known Activations