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

    Neuronpedia

    INDEX
    Explanations

    dub

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (schedule
    -0.07
    fat
    -0.06
     glyphs
    -0.06
     jinak
    -0.06
     Bloom
    -0.06
     fruit
    -0.06
    levels
    -0.06
     interference
    -0.06
     Québec
    -0.06
     hemorrh
    -0.06
    POSITIVE LOGITS
    urence
    0.07
    �
    0.07
    ub
    0.06
    igail
    0.06
    (tcp
    0.06
    UB
    0.06
    wealth
    0.06
    าระ
    0.06
    dro
    0.06
     counterpart
    0.06
    Act Density 0.001%

    No Known Activations