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

    Neuronpedia

    INDEX
    Explanations

    ]

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Soph
    -0.07
     freeway
    -0.06
    _prob
    -0.06
     tremend
    -0.06
    766
    -0.06
    62
    -0.06
     divorced
    -0.06
    source
    -0.05
    av
    -0.05
     premise
    -0.05
    POSITIVE LOGITS
    _excel
    0.07
     olm
    0.07
     cyk
    0.07
    akest
    0.07
    .getvalue
    0.06
    แจ
    0.06
     ignite
    0.06
    oti
    0.06
    онах
    0.06
    ılığıyla
    0.06
    Act Density 0.023%

    No Known Activations