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

    Neuronpedia

    INDEX
    Explanations

    informant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     правда
    -0.07
    قف
    -0.07
     Verizon
    -0.07
     Regression
    -0.06
     Gates
    -0.06
     бенз
    -0.06
     ท
    -0.06
     Regents
    -0.06
    Resources
    -0.06
    visions
    -0.06
    POSITIVE LOGITS
    ební
    0.06
     excessive
    0.06
    .crypto
    0.06
    �
    0.06
    IMER
    0.06
     rost
    0.06
     fitting
    0.06
     stands
    0.06
    Ju
    0.06
     charity
    0.06
    Act Density 0.003%

    No Known Activations