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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _intr
    -0.08
    vault
    -0.07
    administr
    -0.07
    provided
    -0.07
    avatar
    -0.07
     entr
    -0.06
    (check
    -0.06
    itures
    -0.06
    everyone
    -0.06
    _conv
    -0.06
    POSITIVE LOGITS
    春夏
    0.07
     Yö
    0.07
    '>$
    0.07
    嗞
    0.07
     =>
    0.07
     letras
    0.07
    ゃ
    0.07
    绲
    0.07
    Mocks
    0.07
     RUN
    0.06
    Act Density 0.012%

    No Known Activations