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

    Neuronpedia

    INDEX
    Explanations

    aster (substring)

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fore
    -0.07
     lign
    -0.06
     magg
    -0.06
    .elem
    -0.06
     fortunately
    -0.06
    533
    -0.06
     bun
    -0.06
     withhold
    -0.06
     halo
    -0.06
     Kidd
    -0.06
    POSITIVE LOGITS
    cast
    0.19
     casting
    0.16
     Casting
    0.16
    casting
    0.15
    CAST
    0.14
    icast
    0.13
    casts
    0.12
     Castro
    0.11
     caster
    0.11
    caster
    0.11
    Act Density 0.012%

    No Known Activations