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

    Neuronpedia

    INDEX
    Explanations

    help/documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    åĽ½éĻħåľ¨çº¿
    -0.28
    æ³¢
    -0.27
    etration
    -0.24
     wave
    -0.24
    ervals
    -0.24
    ictionary
    -0.24
    ud
    -0.24
    ormsg
    -0.24
    .gnu
    -0.24
    é¹Ħ
    -0.24
    POSITIVE LOGITS
    ìŀĦ
    0.28
    aste
    0.27
    curity
    0.26
    /sign
    0.26
    ç¼
    0.25
     Whilst
    0.25
     prefixes
    0.25
    æ³ī
    0.25
    aac
    0.25
    sticky
    0.25
    Act Density 0.000%

    No Known Activations