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

    Neuronpedia

    INDEX
    Explanations

    time duration

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     In
    -0.07
    post
    -0.06
     neutrality
    -0.06
    _decision
    -0.06
     decision
    -0.06
     Sole
    -0.06
    _growth
    -0.06
    descending
    -0.06
     actor
    -0.06
    2
    -0.06
    POSITIVE LOGITS
    ügen
    0.06
    !');↵
    0.06
    ำ
    0.06
    ouston
    0.06
     věci
    0.06
    -plugin
    0.06
    €“
    0.06
     equipe
    0.06
    _DOC
    0.06
    ucken
    0.06
    Act Density 0.060%

    No Known Activations