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

    Neuronpedia

    INDEX
    Explanations

    WCAG accessibility standards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     atunci
    0.49
    Thickness
    0.49
    団
    0.48
    ان
    0.47
    माजिक
    0.45
    .
    0.45
    اب
    0.45
    гээ
    0.45
    don
    0.44
    サンプル
    0.44
    POSITIVE LOGITS
     返回
    0.58
     两
    0.53
    owały
    0.52
     πολλ
    0.51
     incor
    0.51
     ويم
    0.50
    úncia
    0.50
     Tycho
    0.50
     posição
    0.50
    uele
    0.49
    Act Density 0.000%

    No Known Activations