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

    Neuronpedia

    INDEX
    Explanations

    erotica

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ta
    -0.06
    _FIRE
    -0.06
    ρα
    -0.06
     trem
    -0.06
    stackpath
    -0.06
     speeding
    -0.06
    491
    -0.06
     ['.
    -0.06
     піз
    -0.06
     STA
    -0.06
    POSITIVE LOGITS
    came
    0.07
    віль
    0.06
     equation
    0.06
     owing
    0.06
     Launch
    0.06
    ovah
    0.06
     narratives
    0.06
     ensued
    0.06
     exchanged
    0.06
    海道
    0.06
    Act Density 0.025%

    No Known Activations