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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ImGui
    -0.07
    وذ
    -0.07
     maximize
    -0.06
     Voc
    -0.06
    Todd
    -0.06
    <Data
    -0.06
    уп
    -0.06
    Moon
    -0.06
     Mim
    -0.06
     Uh
    -0.06
    POSITIVE LOGITS
     reimbursement
    0.06
    Lf
    0.06
     solitary
    0.06
     similar
    0.06
    ็กชาย
    0.06
     unidentified
    0.06
    ินการ
    0.06
    -rel
    0.06
    异常
    0.06
    dsl
    0.06
    Act Density 0.024%

    No Known Activations