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

    Neuronpedia

    INDEX
    Explanations

    past

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Como
    -0.07
     Technical
    -0.07
     mulheres
    -0.06
     پس
    -0.06
    NEG
    -0.06
     Mosque
    -0.06
    ERICAN
    -0.06
    ського
    -0.06
     affidavit
    -0.06
     voluntary
    -0.06
    POSITIVE LOGITS
    errorCode
    0.07
     Waiting
    0.07
    irling
    0.07
    (metric
    0.07
    ifiers
    0.07
    inel
    0.06
    UCT
    0.06
    _saved
    0.06
    adr
    0.06
    .singleton
    0.06
    Act Density 0.051%

    No Known Activations