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

    Neuronpedia

    INDEX
    Explanations

    arth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ydro
    -0.07
    _requested
    -0.06
    Evaluation
    -0.06
    <message
    -0.06
     workflows
    -0.06
    לא
    -0.06
     זמן
    -0.06
     '['
    -0.06
     mistakenly
    -0.06
    まだまだ
    -0.06
    POSITIVE LOGITS
    стран
    0.08
    _warn
    0.07
    stände
    0.07
    ее
    0.06
     phú
    0.06
    協會
    0.06
     eql
    0.06
     الهند
    0.06
    JKLM
    0.06
     endlessly
    0.06
    Act Density 0.026%

    No Known Activations