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

    Neuronpedia

    INDEX
    Explanations

    improve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Produces
    -0.07
     Merkel
    -0.07
     mName
    -0.07
     mocker
    -0.07
    .gpu
    -0.07
     RTAL
    -0.07
    loub
    -0.06
    _emlrt
    -0.06
    []=$
    -0.06
    OOD
    -0.06
    POSITIVE LOGITS
     Bud
    0.07
     Resp
    0.07
    Bonus
    0.07
     denounced
    0.06
    .Stage
    0.06
     clearInterval
    0.06
     Nicar
    0.06
     Cad
    0.06
    には
    0.06
     northeast
    0.06
    Act Density 0.021%

    No Known Activations