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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _agent
    -0.06
    _cred
    -0.06
    Website
    -0.06
    .Nodes
    -0.06
     też
    -0.06
     अपन
    -0.06
    Inserted
    -0.06
     altercation
    -0.06
    _order
    -0.06
     pretending
    -0.06
    POSITIVE LOGITS
    าค
    0.07
    +"'
    0.07
     झ
    0.07
     bounce
    0.06
    .cljs
    0.06
     pressures
    0.06
    งาน
    0.06
     gli
    0.06
    ...↵
    0.06
    】↵
    0.06
    Act Density 0.013%

    No Known Activations