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

    Neuronpedia

    INDEX
    Explanations

    Time duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     False
    -0.07
     blast
    -0.07
     detection
    -0.07
    ΕΥ
    -0.07
     Bam
    -0.06
    PM
    -0.06
     Detection
    -0.06
     shielding
    -0.06
    else
    -0.06
    _adc
    -0.06
    POSITIVE LOGITS
     dej
    0.07
    には
    0.07
    ряду
    0.06
    與
    0.06
     aprend
    0.06
     dismay
    0.06
    :\/\/
    0.06
    //@
    0.06
     unwilling
    0.06
     oprav
    0.06
    Act Density 0.009%

    No Known Activations