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

    Neuronpedia

    INDEX
    Explanations

    mod + keyboard shortcuts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <?>
    0.46
     err
    0.45
    .,"
    0.45
    ->
    0.43
     hal
    0.43
     ans
    0.43
     pam
    0.43
     god
    0.42
     fui
    0.42
     absorb
    0.42
    POSITIVE LOGITS
    ných
    0.55
    ває
    0.50
     नागरिक
    0.49
     британ
    0.49
    ве
    0.47
    ене
    0.47
    ेक्स
    0.47
    ná
    0.47
    ване
    0.47
    американ
    0.46
    Act Density 0.006%

    No Known Activations