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

    Neuronpedia

    INDEX
    Explanations

    comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     کاربرد
    -0.07
     ولي
    -0.07
     crop
    -0.06
    	rd
    -0.06
     cbd
    -0.06
    undos
    -0.06
    Want
    -0.06
     الوف
    -0.06
     riv
    -0.06
    "
    -0.06
    POSITIVE LOGITS
     payday
    0.06
     eighteen
    0.06
    .number
    0.06
     Bitcoin
    0.06
     durch
    0.06
     зак
    0.06
     basename
    0.06
     Salmon
    0.06
    _logic
    0.06
    αρά
    0.05
    Act Density 0.068%

    No Known Activations