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

    Neuronpedia

    INDEX
    Explanations

    from for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     parseFloat
    -0.07
    .box
    -0.07
    赞
    -0.07
    -е
    -0.06
    blue
    -0.06
     hunt
    -0.06
     speaking
    -0.06
     хот
    -0.06
    楽
    -0.06
    achu
    -0.06
    POSITIVE LOGITS
     Disney
    0.07
     شف
    0.06
     Prometheus
    0.06
     directives
    0.06
    bench
    0.06
    Refer
    0.06
     PCIe
    0.06
    FFFF
    0.06
    “(
    0.06
     良
    0.06
    Act Density 0.001%

    No Known Activations