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

    Neuronpedia

    INDEX
    Explanations

    arrows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wrth
    -0.07
    ాష్ట్ర
    -0.07
    flags
    -0.07
    ויה
    -0.07
    స్య
    -0.07
    chain
    -0.07
    దేశ్
    -0.07
    %s
    -0.07
    _flags
    -0.07
     أنها
    -0.07
    POSITIVE LOGITS
    REN
    0.08
     Lifetime
    0.08
     REN
    0.08
     život
    0.08
     வாழ்க்க
    0.08
    생활
    0.08
     cé
    0.08
     LIFE
    0.08
     생활
    0.08
     lifestyles
    0.08
    Act Density 0.001%

    No Known Activations