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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     promoting
    -0.07
    arak
    -0.07
     equipments
    -0.07
    _bit
    -0.06
     της
    -0.06
    ERRU
    -0.06
     charges
    -0.06
    PRE
    -0.06
    moire
    -0.06
     ambassador
    -0.06
    POSITIVE LOGITS
    apus
    0.06
    �
    0.06
    」「
    0.06
     disciplined
    0.06
    incinn
    0.06
     absolut
    0.06
     consequential
    0.06
    voř
    0.06
     uzav
    0.06
    ::|
    0.06
    Act Density 0.018%

    No Known Activations