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

    Neuronpedia

    INDEX
    Explanations

    minimum

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marcos
    -0.06
     Cay
    -0.06
     genocide
    -0.06
     вересня
    -0.06
     clusters
    -0.06
    SY
    -0.06
    ๊ก
    -0.06
     redundant
    -0.06
     wollen
    -0.06
    ARR
    -0.06
    POSITIVE LOGITS
     minimum
    0.10
     Minimum
    0.09
    .MIN
    0.08
    Minimum
    0.07
     minValue
    0.07
    مل
    0.07
    ":"'
    0.06
     фот
    0.06
    ).'</
    0.06
    ToRemove
    0.06
    Act Density 0.010%

    No Known Activations