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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     навіть
    -0.06
    альные
    -0.06
     Sinh
    -0.06
     �
    -0.06
    >')
    -0.06
     Experimental
    -0.06
    .booking
    -0.06
    _HOUR
    -0.06
    .green
    -0.06
    .prod
    -0.06
    POSITIVE LOGITS
     GETGLOBAL
    0.06
    BB
    0.06
    ubre
    0.06
     Rehab
    0.06
    Zoom
    0.06
    】↵↵
    0.06
     získat
    0.06
     comunidad
    0.06
     )↵
    0.06
     destino
    0.06
    Act Density 0.012%

    No Known Activations