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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ladies
    -0.07
     Pol
    -0.07
    _hook
    -0.07
     Fors
    -0.06
     กล
    -0.06
     Imam
    -0.06
    Bot
    -0.06
    arpa
    -0.06
     imag
    -0.06
    ъек
    -0.06
    POSITIVE LOGITS
    爽
    0.07
     madrid
    0.07
    .loader
    0.06
    چار
    0.06
     respondent
    0.06
    Roles
    0.06
     оскільки
    0.06
    =y
    0.06
    －
    0.06
    839
    0.06
    Act Density 0.039%

    No Known Activations