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

    Neuronpedia

    INDEX
    Explanations

    PHP code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guy
    -0.07
     EXCEPTION
    -0.06
     problème
    -0.06
    Sorting
    -0.06
     ذ
    -0.06
    抱
    -0.06
     guys
    -0.06
    PHA
    -0.06
     modificar
    -0.06
     ست
    -0.06
    POSITIVE LOGITS
    -inner
    0.07
    _ABI
    0.07
     bark
    0.07
     distractions
    0.07
     listened
    0.06
     HOH
    0.06
     opr
    0.06
     Machinery
    0.06
    _params
    0.06
     الاتحاد
    0.06
    Act Density 0.023%

    No Known Activations