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

    Neuronpedia

    INDEX
    Explanations

    categorization methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    usement
    -0.07
     tourist
    -0.07
    .try
    -0.07
     shook
    -0.06
    Dash
    -0.06
    doch
    -0.06
     vor
    -0.06
     projekt
    -0.06
     Thing
    -0.06
    _Left
    -0.06
    POSITIVE LOGITS
    Insp
    0.06
    ]
↵
    0.06
     평
    0.06
    Verification
    0.06
     làng
    0.06
    _SPLIT
    0.06
    pciones
    0.06
     específ
    0.06
    .BO
    0.06
     CONTRIBUT
    0.06
    Act Density 0.216%

    No Known Activations