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

    Neuronpedia

    INDEX
    Explanations

    say "s word"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _EXP
    -0.07
    ]")]↵
    -0.07
    -0.07
    ��
    -0.07
    .vote
    -0.07
    ğu
    -0.07
     Danish
    -0.06
    -0.06
    打击
    -0.06
     resulted
    -0.06
    POSITIVE LOGITS
     Lage
    0.07
    (%
    0.07
    に対して
    0.07
    背
    0.07
    工程机械
    0.07
    hic
    0.06
     seab
    0.06
    ADB
    0.06
    舟
    0.06
    xbf
    0.06
    Act Density 0.021%

    No Known Activations