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

    Neuronpedia

    INDEX
    Explanations

    signpost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Sign
    0.55
     signing
    0.55
     Signing
    0.55
    signing
    0.54
    Signing
    0.52
     Sign
    0.49
    签
    0.49
    サイン
    0.49
    sign
    0.47
    签名
    0.47
    POSITIVE LOGITS
    boards
    0.56
    ifiers
    0.51
    board
    0.50
    posts
    0.50
    resses
    0.47
    ails
    0.45
    boarding
    0.44
    ials
    0.43
    BOARD
    0.43
    essive
    0.42
    Act Density 0.005%

    No Known Activations