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

    Neuronpedia

    INDEX
    Explanations

    first-person "to be"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     IMDb
    -0.06
     bypass
    -0.06
    вал
    -0.06
    andidates
    -0.06
    ATALOG
    -0.06
     Address
    -0.06
     HACK
    -0.06
    /var
    -0.06
     하는
    -0.06
     kvinna
    -0.06
    POSITIVE LOGITS
     �
    0.07
     strtolower
    0.07
    .getFirst
    0.06
     softmax
    0.06
     Cain
    0.06
     克
    0.06
     uống
    0.06
     uz
    0.06
    :UIControlStateNormal
    0.06
     crim
    0.06
    Act Density 0.069%

    No Known Activations