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

    Neuronpedia

    INDEX
    Explanations

    upyter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abi
    -0.07
    диви
    -0.07
     faulty
    -0.07
    oustic
    -0.07
    �
    -0.07
    ивания
    -0.06
    Ch
    -0.06
    .state
    -0.06
    应
    -0.06
    ег
    -0.06
    POSITIVE LOGITS
     phạm
    0.07
    개월
    0.06
    一区
    0.06
     AccessToken
    0.06
     PRIV
    0.06
     dramatic
    0.06
     interv
    0.06
    tuğ
    0.06
     warrants
    0.06
     defaultProps
    0.06
    Act Density 0.000%

    No Known Activations