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

    Neuronpedia

    INDEX
    Explanations

    describing methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Reality
    -0.07
    "]).
    -0.07
    �
    -0.07
     Circuit
    -0.07
     stakeholders
    -0.06
     earnings
    -0.06
     checkpoints
    -0.06
    ']").
    -0.06
    mh
    -0.06
    »↵
    -0.06
    POSITIVE LOGITS
    wers
    0.06
     fotos
    0.06
     neuen
    0.06
    íše
    0.06
     используют
    0.06
    自分の
    0.06
    benhavn
    0.06
    svm
    0.06
    убли
    0.06
     esper
    0.06
    Act Density 0.073%

    No Known Activations