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

    Neuronpedia

    INDEX
    Explanations

    offering help with tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     legít
    0.53
     realización
    0.52
     honda
    0.52
     méthode
    0.51
     medicamento
    0.50
     factura
    0.50
    胼
    0.49
    ައް
    0.49
    মিনা
    0.49
    Penumpang
    0.48
    POSITIVE LOGITS
    i
    0.61
    el
    0.55
    ör
    0.50
    in
    0.48
    et
    0.47
    ds
    0.47
    ui
    0.46
    ih
    0.46
    iron
    0.46
    ing
    0.46
    Act Density 0.005%

    No Known Activations