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

    Neuronpedia

    INDEX
    Explanations

    force

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Condition
    -0.07
    団
    -0.07
    _save
    -0.06
    versation
    -0.06
     در
    -0.06
    раг
    -0.06
    民主
    -0.06
    oothing
    -0.06
    .mkdir
    -0.06
    ασ
    -0.06
    POSITIVE LOGITS
    الد
    0.07
    ByExample
    0.07
     spielen
    0.07
     �
    0.07
     Red
    0.06
    ских
    0.06
     rebuilt
    0.06
     BİR
    0.06
     sữa
    0.06
     aquel
    0.06
    Act Density 0.010%

    No Known Activations