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

    Neuronpedia

    INDEX
    Explanations

    Methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wolfe
    -0.07
     Daly
    -0.07
     gating
    -0.07
    处理
    -0.06
    GV
    -0.06
     collapses
    -0.06
    елем
    -0.06
    aby
    -0.06
    Vs
    -0.06
    isz
    -0.06
    POSITIVE LOGITS
     orgán
    0.07
    ."',
    0.06
    $password
    0.06
    .trailing
    0.06
    ('/:
    0.06
    Methods
    0.06
    substring
    0.06
     proceed
    0.06
    -know
    0.06
    688
    0.06
    Act Density 0.008%

    No Known Activations