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

    Neuronpedia

    INDEX
    Explanations

    colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    chts
    -0.07
     Kumar
    -0.06
     perverse
    -0.06
     cứ
    -0.06
     دهه
    -0.06
    religious
    -0.06
    سبب
    -0.06
    Classifier
    -0.06
    إ
    -0.06
    stop
    -0.06
    POSITIVE LOGITS
    .start
    0.07
     lö
    0.06
    ;<
    0.06
     Luna
    0.06
    :"
    0.06
     Redistribution
    0.06
    -len
    0.06
    .builder
    0.06
    AZ
    0.06
    .MiddleRight
    0.06
    Act Density 0.067%

    No Known Activations