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

    Neuronpedia

    INDEX
    Explanations

    sweet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    dfd
    -0.08
    /^
    -0.07
     hrs
    -0.07
    éis
    -0.06
    @\
    -0.06
    /disc
    -0.06
    orsche
    -0.06
    cca
    -0.06
    +v
    -0.06
    others
    -0.06
    POSITIVE LOGITS
    244
    0.06
    �
    0.06
    实在
    0.06
     площад
    0.06
     STYLE
    0.06
    Ư�
    0.06
    少女
    0.06
     Cosby
    0.06
     Skyl
    0.06
    setEnabled
    0.06
    Act Density 0.007%

    No Known Activations