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

    Neuronpedia

    INDEX
    Explanations

    time zones

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    چ
    -0.07
     embracing
    -0.07
    FRING
    -0.07
    鳴
    -0.07
     ry
    -0.06
    bits
    -0.06
    .presenter
    -0.06
    ors
    -0.06
     Mapping
    -0.06
     fellowship
    -0.06
    POSITIVE LOGITS
    	TokenName
    0.06
     Pixar
    0.06
    ******/
    0.06
     Moss
    0.06
    sí
    0.06
     sağlam
    0.06
     downside
    0.06
     Serve
    0.06
     hrs
    0.06
     INVALID
    0.06
    Act Density 0.006%

    No Known Activations