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

    Neuronpedia

    INDEX
    Explanations

    Act/Law

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    promotion
    -0.07
    .languages
    -0.07
    -League
    -0.07
     poop
    -0.07
     BaseController
    -0.06
    -0.06
    _S
    -0.06
     implication
    -0.06
     сю
    -0.06
    evaluation
    -0.06
    POSITIVE LOGITS
    DOC
    0.06
    .LinearLayoutManager
    0.06
     rnn
    0.06
    redict
    0.06
    がお
    0.06
    něji
    0.06
    enor
    0.06
    (encoded
    0.06
    _ASSUME
    0.06
    nat
    0.06
    Act Density 0.017%

    No Known Activations