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

    Neuronpedia

    INDEX
    Explanations

    phenomenon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pie
    -0.07
     tails
    -0.07
     juicy
    -0.07
     Arctic
    -0.06
     draped
    -0.06
     trig
    -0.06
     XY
    -0.06
     indent
    -0.06
     braz
    -0.06
     Christie
    -0.06
    POSITIVE LOGITS
     phenomenon
    0.08
     phenomena
    0.08
     opět
    0.08
    .prompt
    0.08
    _PACKET
    0.08
    _subtype
    0.07
     노하우
    0.07
    γα
    0.07
     üniversit
    0.07
    ph
    0.07
    Act Density 0.007%

    No Known Activations