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
    ::*
    -0.06
    _verified
    -0.06
     utiliz
    -0.06
    .fromFunction
    -0.06
    }'.
    -0.06
     información
    -0.06
     }}
↵
    -0.06
    ála
    -0.06
    action
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     interiors
    0.07
     Snake
    0.06
     Lips
    0.06
     hull
    0.06
     conservatism
    0.06
    Trivia
    0.06
    亡
    0.06
    emiz
    0.06
     yak
    0.06
     Giov
    0.06
    Act Density 0.004%

    No Known Activations