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

    Neuronpedia

    INDEX
    Explanations

    when all is said

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bbox
    -0.07
     flo
    -0.07
    (sq
    -0.07
     evac
    -0.07
     biodiversity
    -0.07
     Bare
    -0.06
     Legs
    -0.06
     Prec
    -0.06
     evalu
    -0.06
     ));
↵
    -0.06
    POSITIVE LOGITS
     tantra
    0.07
     다음
    0.06
    ちゃ
    0.06
    ombat
    0.06
    uristic
    0.06
     finan
    0.05
    -fired
    0.05
    里面
    0.05
    IfNeeded
    0.05
    ΗΝ
    0.05
    Act Density 0.025%

    No Known Activations