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

    Neuronpedia

    INDEX
    Explanations

    home

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Random
    -0.06
     giveaway
    -0.06
     Needle
    -0.06
     Thanksgiving
    -0.06
     PH
    -0.06
    Better
    -0.06
     coloring
    -0.06
    最
    -0.06
    ục
    -0.06
     посл
    -0.06
    POSITIVE LOGITS
    (MouseEvent
    0.07
    çe
    0.06
    wow
    0.06
    *g
    0.06
    하며
    0.06
    vero
    0.06
    rete
    0.06
    mute
    0.06
    yleft
    0.06
    /Instruction
    0.06
    Act Density 0.002%

    No Known Activations