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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cue
    -0.07
    /count
    -0.07
    ("<?
    -0.07
     Istanbul
    -0.06
    ACEMENT
    -0.06
    dropout
    -0.06
     Levine
    -0.06
    DAC
    -0.06
     Signals
    -0.06
    _SEGMENT
    -0.06
    POSITIVE LOGITS
     ReturnValue
    0.07
     indef
    0.07
    -host
    0.07
     бать
    0.07
     ekonom
    0.06
     sqlite
    0.06
    aurus
    0.06
     MongoDB
    0.06
    torch
    0.06
    mongodb
    0.06
    Act Density 0.171%

    No Known Activations