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

    Neuronpedia

    INDEX
    Explanations

    what

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    autiful
    -0.07
     LED
    -0.07
     bitte
    -0.07
    -opening
    -0.06
     tunnel
    -0.06
     Fort
    -0.06
    :@"%@
    -0.06
     uk
    -0.06
     Kolkata
    -0.06
    /'+
    -0.06
    POSITIVE LOGITS
     fotoğraf
    0.07
    AUD
    0.07
     nevertheless
    0.06
    _Key
    0.06
    splash
    0.06
    どこ
    0.06
    三三三三
    0.06
     stash
    0.06
     bahsed
    0.06
     discovery
    0.06
    Act Density 0.015%

    No Known Activations