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

    Neuronpedia

    INDEX
    Explanations

    inherent scalability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ဤ
    0.42
    ച്ചി
    0.40
    😭😭
    0.40
    চরা
    0.40
     गेंदबाजों
    0.40
     docteur
    0.40
     GetComponent
    0.40
    Clientes
    0.39
     ঘণ্টায়
    0.39
    '?
    0.38
    POSITIVE LOGITS
     cumbersome
    0.41
    巢
    0.41
    pyridine
    0.41
     marg
    0.39
     susceptibility
    0.39
    am
    0.38
    arks
    0.38
    arb
    0.38
     concise
    0.38
    oven
    0.37
    Act Density 0.000%

    No Known Activations