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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jahres
    -0.08
     Hải
    -0.07
     GEN
    -0.06
     Hao
    -0.06
    .minecraftforge
    -0.06
    _FLOW
    -0.06
     Mystic
    -0.06
    460
    -0.06
     vp
    -0.06
     Bayern
    -0.06
    POSITIVE LOGITS
    maries
    0.07
    edback
    0.07
    ومات
    0.07
    (job
    0.07
     being
    0.06
     jerseys
    0.06
    لیل
    0.06
    Usage
    0.06
    uddenly
    0.06
    εί
    0.06
    Act Density 0.000%

    No Known Activations