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

    Neuronpedia

    INDEX
    Explanations

    ul

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AWN
    -0.08
    ao
    -0.07
     sandbox
    -0.07
    ">(
    -0.07
    ��
    -0.07
    apot
    -0.07
    ́t
    -0.07
    amak
    -0.06
    '(
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Wrong
    0.06
    IsEmpty
    0.06
     rinse
    0.06
     somewhere
    0.06
     تقد
    0.06
     lightly
    0.06
    ởi
    0.06
    부
    0.06
    üml
    0.06
    Newton
    0.06
    Act Density 0.003%

    No Known Activations