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

    Neuronpedia

    INDEX
    Explanations

    A

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tx
    -0.07
    けない
    -0.06
     killing
    -0.06
    straint
    -0.06
     entreprene
    -0.06
     provision
    -0.06
    tagName
    -0.06
     нічого
    -0.06
     indeed
    -0.06
     continents
    -0.06
    POSITIVE LOGITS
    庭
    0.06
     бух
    0.06
     #-}↵↵
    0.06
     criminals
    0.06
     کردن
    0.06
    μος
    0.06
     Criminal
    0.06
    auga
    0.06
    -vs
    0.06
     accountability
    0.06
    Act Density 0.010%

    No Known Activations