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

    Neuronpedia

    INDEX
    Explanations

    battery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⤦
    -0.08
    遞
    -0.08
    杜
    -0.07
    ру
    -0.07
    ��
    -0.07
    '})↵
    -0.07
    ier
    -0.07
    /platform
    -0.06
    𝐌
    -0.06
    ardo
    -0.06
    POSITIVE LOGITS
    エネルギー
    0.07
    icture
    0.07
    }{$
    0.07
    porno
    0.07
    吃惊
    0.07
     wow
    0.07
    /create
    0.07
    requirements
    0.07
     shootings
    0.07
     {{↵
    0.07
    Act Density 0.022%

    No Known Activations