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

    Neuronpedia

    INDEX
    Explanations

    WHATSOEVER

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    flush
    -0.08
    _part
    -0.07
     confort
    -0.07
    뜰
    -0.07
     broke
    -0.07
    疏导
    -0.07
    .b
    -0.07
    b
    -0.07
    },${
    -0.07
    au
    -0.07
    POSITIVE LOGITS
    gam
    0.07
     venture
    0.07
    "));
↵
↵
    0.07
     מאפשר
    0.07
    Theta
    0.07
    鬼
    0.06
    _decision
    0.06
    �
    0.06
     mole
    0.06
    decision
    0.06
    Act Density 0.001%

    No Known Activations