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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Gro
    -0.07
    ')}}↵
    -0.07
    `;↵
    -0.06
    _dl
    -0.06
     kırmızı
    -0.06
    STREAM
    -0.06
    _rpc
    -0.06
     Crimea
    -0.06
    ात
    -0.06
     almonds
    -0.06
    POSITIVE LOGITS
     Notice
    0.06
     cuenta
    0.06
    _Param
    0.06
    "She
    0.06
    _updated
    0.06
     Shin
    0.06
     kapit
    0.06
     activates
    0.06
    $res
    0.06
     Wage
    0.06
    Act Density 0.040%

    No Known Activations