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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    olve
    -0.06
    يين
    -0.06
    profits
    -0.06
    쇼
    -0.06
     Spencer
    -0.06
    Moves
    -0.06
     errmsg
    -0.06
    legg
    -0.06
    ald
    -0.06
     ци
    -0.06
    POSITIVE LOGITS
     reimburse
    0.07
    semantic
    0.07
    ็นอ
    0.07
    だけど
    0.07
     Embedded
    0.06
    看到
    0.06
     такі
    0.06
     Ank
    0.06
     contemplated
    0.06
     activate
    0.06
    Act Density 0.025%

    No Known Activations