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

    Neuronpedia

    INDEX
    Explanations

    code/formulas

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dismiss
    -0.07
     luz
    -0.07
    erne
    -0.07
    ration
    -0.07
    ote
    -0.07
    rats
    -0.06
    93
    -0.06
    Aside
    -0.06
    attery
    -0.06
     station
    -0.06
    POSITIVE LOGITS
    ('_',
    0.07
     siden
    0.06
    .amazon
    0.06
    大的
    0.06
    >.</
    0.06
     настоя
    0.06
     hedef
    0.06
    ΄
    0.06
    mazon
    0.06
    .</
    0.06
    Act Density 0.005%

    No Known Activations