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

    Neuronpedia

    INDEX
    Explanations

    narrative snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ισε
    -0.07
    alter
    -0.06
     signaling
    -0.06
     offences
    -0.06
    _expiry
    -0.06
    ((
    -0.06
     тогда
    -0.06
    领导
    -0.06
     gamle
    -0.06
     membrane
    -0.06
    POSITIVE LOGITS
    _leader
    0.06
     subcontract
    0.06
    .GetFileName
    0.06
     �
    0.06
     lief
    0.06
    egal
    0.06
    vent
    0.06
    .Config
    0.06
     programmed
    0.06
    otas
    0.06
    Act Density 0.041%

    No Known Activations