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

    Neuronpedia

    INDEX
    Explanations

    import

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    риф
    -0.07
     Performing
    -0.07
     Griffin
    -0.06
     graphics
    -0.06
    -{
    -0.06
     گی
    -0.06
     юрид
    -0.06
     stripes
    -0.06
    transition
    -0.06
    Z
    -0.06
    POSITIVE LOGITS
    -automatic
    0.07
    集中
    0.07
     đương
    0.06
    connector
    0.06
    .abstract
    0.06
     ->
    0.06
     �
    0.06
     ae
    0.06
     ASAP
    0.06
    -redux
    0.06
    Act Density 0.008%

    No Known Activations