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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ameleon
    -0.07
     angi
    -0.06
     Rosie
    -0.06
     Glo
    -0.06
     daar
    -0.06
     insistence
    -0.06
     Douglas
    -0.06
    :`~
    -0.06
     المؤ
    -0.06
    Seleccione
    -0.06
    POSITIVE LOGITS
    üf
    0.07
     �
    0.07
     verifier
    0.07
    ینی
    0.07
     Murray
    0.07
    _axes
    0.06
    OU
    0.06
     examined
    0.06
     aws
    0.06
     Indies
    0.06
    Act Density 0.000%

    No Known Activations