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

    Neuronpedia

    INDEX
    Explanations

    Time or deadlines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hoffman
    -0.07
     rout
    -0.07
     Liability
    -0.06
     deer
    -0.06
     StringWriter
    -0.06
    igsaw
    -0.06
    '];?></
    -0.06
    exo
    -0.06
    ються
    -0.06
     Manchester
    -0.06
    POSITIVE LOGITS
    	names
    0.07
    .Inter
    0.07
     تنظیم
    0.07
    ْن
    0.07
     соз
    0.06
     dokun
    0.06
    	RE
    0.06
    [idx
    0.06
     ölçü
    0.06
    ünüz
    0.06
    Act Density 0.063%

    No Known Activations