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

    Neuronpedia

    INDEX
    Explanations

    numeric sequences

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Quick
    -0.07
    .merge
    -0.07
     Orc
    -0.06
     Trainer
    -0.06
    Everything
    -0.06
    list
    -0.06
    ,U
    -0.06
     busc
    -0.06
    riger
    -0.06
     lesson
    -0.06
    POSITIVE LOGITS
    /values
    0.07
     determining
    0.07
    цький
    0.07
     antique
    0.07
    بات
    0.07
     scram
    0.06
    вався
    0.06
     embry
    0.06
     tòa
    0.06
     DevExpress
    0.06
    Act Density 0.012%

    No Known Activations