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

    Neuronpedia

    INDEX
    Explanations

    Stories with masked identities/Zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     разв
    -0.08
    _embedding
    -0.08
     диаг
    -0.08
    ypes
    -0.08
     kiel
    -0.08
     py
    -0.08
    _embed
    -0.07
     рак
    -0.07
    ogera
    -0.07
     Perry
    -0.07
    POSITIVE LOGITS
     mystérie
    0.16
     enigmatic
    0.15
     mysterious
    0.15
     unidentified
    0.14
     unknown
    0.13
     неизвест
    0.12
     Unknown
    0.12
    Unknown
    0.12
     masked
    0.12
    匿名
    0.12
    Act Density 0.050%

    No Known Activations