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

    Neuronpedia

    INDEX
    Explanations

    verbs "to be" and "think"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (suffix
    -0.08
    婚后
    -0.07
    .NoArgsConstructor
    -0.07
    _func
    -0.07
    ategoria
    -0.07
    葑
    -0.07
     feminism
    -0.07
    AssignableFrom
    -0.07
    getView
    -0.07
    _passwd
    -0.06
    POSITIVE LOGITS
    补
    0.07
    (XML
    0.07
    够
    0.07
    ()\
    0.07
    تهم
    0.07
    CAP
    0.07
    []);↵
    0.07
    tep
    0.07
    .escape
    0.06
    _tim
    0.06
    Act Density 0.110%

    No Known Activations