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

    Neuronpedia

    INDEX
    Explanations

    technical/unstructured language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Unsupported
    -0.07
     "";↵↵
    -0.07
    .setdefault
    -0.07
     drug
    -0.07
    pod
    -0.07
    .single
    -0.06
     famously
    -0.06
     Square
    -0.06
    _parameter
    -0.06
    DATA
    -0.06
    POSITIVE LOGITS
    (completion
    0.07
    .Secret
    0.07
     etkisi
    0.07
     firestore
    0.07
     bourgeois
    0.07
    ούς
    0.07
     plais
    0.06
     budeme
    0.06
    vc
    0.06
    xce
    0.06
    Act Density 0.000%

    No Known Activations