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

    Neuronpedia

    INDEX
    Explanations

    production

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oultry
    -0.07
     Evo
    -0.07
    ];↵↵
    -0.06
    neg
    -0.06
     заболева
    -0.06
     throwError
    -0.06
    <Result
    -0.06
     Floors
    -0.06
     lethal
    -0.06
    //}↵↵
    -0.06
    POSITIVE LOGITS
    概
    0.06
    stats
    0.06
    olars
    0.06
    _unlock
    0.06
    ceipt
    0.06
     vault
    0.06
     POLITICO
    0.06
     booze
    0.06
     summon
    0.06
    妻
    0.06
    Act Density 0.012%

    No Known Activations