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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Handle
    -0.07
    الح
    -0.07
     workbook
    -0.07
    	Delete
    -0.06
    一人
    -0.06
    uil
    -0.06
     عاشق
    -0.06
    谋
    -0.06
    ائه
    -0.06
    >false
    -0.06
    POSITIVE LOGITS
     metallic
    0.07
    CSI
    0.07
     php
    0.06
     serialize
    0.06
     peak
    0.06
     CIF
    0.06
    rupa
    0.06
    wizard
    0.06
     cube
    0.06
     taxpayers
    0.06
    Act Density 0.000%

    No Known Activations