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

    Neuronpedia

    INDEX
    Explanations

    quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ">%
    -0.06
    aeper
    -0.06
    almart
    -0.06
     patiently
    -0.06
     Cumhur
    -0.06
     sido
    -0.06
     司
    -0.06
    [slot
    -0.06
    oftware
    -0.06
     Capability
    -0.06
    POSITIVE LOGITS
     Annual
    0.07
    MED
    0.07
     suggestive
    0.07
    เลข
    0.07
    BUM
    0.06
     overcoming
    0.06
    rst
    0.06
    quets
    0.06
     balls
    0.06
    STAT
    0.06
    Act Density 0.002%

    No Known Activations