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

    Neuronpedia

    INDEX
    Explanations

    Embarrassing situations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invited
    -0.07
     {!
    -0.07
     الثاني
    -0.07
     competitors
    -0.06
    Lots
    -0.06
     Grove
    -0.06
     expand
    -0.06
    partment
    -0.06
     bóng
    -0.06
     specialists
    -0.06
    POSITIVE LOGITS
    _il
    0.07
    _sys
    0.06
    plets
    0.06
    ienia
    0.06
    ('<?
    0.06
    ショ
    0.06
     '='
    0.06
    uo
    0.06
    929
    0.06
    -target
    0.06
    Act Density 0.159%

    No Known Activations