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

    Neuronpedia

    INDEX
    Explanations

    of/include

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    켐
    -0.07
    电解
    -0.07
    ference
    -0.07
    có
    -0.07
    tell
    -0.07
    قدير
    -0.07
     shaped
    -0.06
    trand
    -0.06
    Pg
    -0.06
    现金
    -0.06
    POSITIVE LOGITS
     الرياض
    0.07
    ISED
    0.07
    要不要
    0.07
     목
    0.07
    峿
    0.07
    .requireNonNull
    0.07
    なかった
    0.07
    PopMatrix
    0.07
    _Target
    0.07
    _Rem
    0.07
    Act Density 0.005%

    No Known Activations