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

    Neuronpedia

    INDEX
    Explanations

    perspectives, philosophy, and history

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     crossbow
    0.46
     purpure
    0.41
     pistachio
    0.40
     miners
    0.40
    orchid
    0.39
    或其他
    0.39
     poolside
    0.39
    రణ
    0.38
     enclave
    0.38
    Attack
    0.38
    POSITIVE LOGITS
    дят
    0.46
    ଭ
    0.46
     konkur
    0.45
    ش
    0.45
    咉
    0.44
    HOSTNAME
    0.43
    าล
    0.43
    ន់
    0.43
     درست
    0.41
     aceptar
    0.41
    Act Density 0.001%

    No Known Activations