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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (DEFAULT
    -0.07
     CAPITAL
    -0.07
     ATA
    -0.07
    	PORT
    -0.06
    ๚
    -0.06
    alk
    -0.06
    IMO
    -0.06
     Pharmaceutical
    -0.06
     MIT
    -0.06
    _APPS
    -0.06
    POSITIVE LOGITS
    𝐧
    0.07
    🌟
    0.07
    becca
    0.07
     gotten
    0.07
     tg
    0.07
    Nh
    0.07
     rg
    0.07
    聊天
    0.06
     Fetish
    0.06
    เคล
    0.06
    Act Density 0.060%

    No Known Activations