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

    Neuronpedia

    INDEX
    Explanations

    president

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    墐
    -0.07
    peq
    -0.07
    OUCH
    -0.07
     clause
    -0.06
    听到
    -0.06
     thị
    -0.06
    换取
    -0.06
    Ắ
    -0.06
    .ENTER
    -0.06
    gages
    -0.06
    POSITIVE LOGITS
     *(
    0.07
     legion
    0.07
     edición
    0.07
    Rib
    0.07
    _PARAMETERS
    0.07
    ****
    0.07
     basics
    0.07
     kf
    0.07
    星期
    0.07
     acclaimed
    0.07
    Act Density 0.085%

    No Known Activations