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

    Neuronpedia

    INDEX
    Explanations

    were

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    topl
    -0.06
    ecedor
    -0.06
     Chop
    -0.06
     récup
    -0.06
     аг
    -0.06
     협
    -0.06
    нист
    -0.06
    Industrial
    -0.06
    мотря
    -0.06
    .command
    -0.06
    POSITIVE LOGITS
     Married
    0.07
    _DISABLE
    0.07
     Moderate
    0.06
     Orbit
    0.06
     inclusive
    0.06
    的事情
    0.06
     extr
    0.06
    809
    0.06
     Apex
    0.06
    uled
    0.06
    Act Density 0.000%

    No Known Activations