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

    Neuronpedia

    INDEX
    Explanations

    elipsis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    恐
    -0.07
     Springs
    -0.07
     mv
    -0.07
     king
    -0.07
     royal
    -0.06
    ToAdd
    -0.06
     Royal
    -0.06
     Nir
    -0.06
     lake
    -0.06
     GOOD
    -0.06
    POSITIVE LOGITS
    startIndex
    0.07
    .Safe
    0.07
     unlaw
    0.06
     insan
    0.06
    zą
    0.06
     مقدم
    0.06
    ประม
    0.06
    provide
    0.06
    :])
    0.06
    (parts
    0.06
    Act Density 0.007%

    No Known Activations