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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     experiments
    -0.08
    314
    -0.07
     obscure
    -0.06
    _No
    -0.06
     objectives
    -0.06
    _("
    -0.06
    -to
    -0.06
    .Azure
    -0.06
    简
    -0.06
     نزد
    -0.06
    POSITIVE LOGITS
     ACK
    0.08
    Filed
    0.07
    .mac
    0.07
    ',
↵
    0.06
    -request
    0.06
     blah
    0.06
    clc
    0.06
     McM
    0.06
    ODEV
    0.06
     maman
    0.06
    Act Density 0.015%

    No Known Activations