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

    Neuronpedia

    INDEX
    Explanations

    say "ade/adic" endings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _changed
    -0.07
    LAS
    -0.06
     ffmpeg
    -0.06
    ываются
    -0.06
    ATED
    -0.06
    Escape
    -0.06
    检查
    -0.05
    ة
    -0.05
    ющихся
    -0.05
    _api
    -0.05
    POSITIVE LOGITS
    ecx
    0.07
    )(__
    0.07
     hyster
    0.07
    	cf
    0.07
    _Name
    0.07
    productive
    0.07
     quadrant
    0.07
     runoff
    0.06
    _common
    0.06
     IE
    0.06
    Act Density 0.001%

    No Known Activations