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

    Neuronpedia

    INDEX
    Explanations

    brackets and colons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulls
    -0.06
     řízení
    -0.06
     душ
    -0.06
    _FRE
    -0.06
    �
    -0.06
    .rem
    -0.06
     العظ
    -0.06
    (pref
    -0.06
    �
    -0.06
    _FAST
    -0.06
    POSITIVE LOGITS
    Tokens
    0.08
     Acc
    0.08
    .sb
    0.07
     Poison
    0.07
     combos
    0.07
     Entity
    0.07
     Veget
    0.07
     입력
    0.07
    Spawn
    0.07
     Assign
    0.07
    Act Density 0.003%

    No Known Activations