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

    Neuronpedia

    INDEX
    Explanations

    leadership roles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     continúas
    -0.77
    fromnode
    -0.68
    లాలు
    -0.64
     RIPRODUZIONE
    -0.63
    новниш
    -0.63
     betweenstory
    -0.61
    GEBURTSDATUM
    -0.60
     Italijanski
    -0.53
    glises
    -0.53
     wrinkles
    -0.52
    POSITIVE LOGITS
    +#+
    0.56
     president
    0.53
    AnchorStyles
    0.52
    sonian
    0.51
     ISNI
    0.50
    \{\\
    0.50
     director
    0.48
    nbt
    0.47
    peper
    0.46
     Вікіпе
    0.46
    Act Density 0.002%

    No Known Activations