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

    Neuronpedia

    INDEX
    Explanations

    geometric shapes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    reward
    -0.06
    /manual
    -0.06
    dismiss
    -0.06
    _TLS
    -0.06
    Live
    -0.06
    URLRequest
    -0.06
     дії
    -0.06
    -fold
    -0.06
    ").↵↵
    -0.06
    meeting
    -0.06
    POSITIVE LOGITS
     Roosevelt
    0.07
     Edinburgh
    0.07
     threesome
    0.07
    	util
    0.06
     실�
    0.06
     hairst
    0.06
    pars
    0.06
     هل
    0.06
    اران
    0.06
    (tableName
    0.06
    Act Density 0.075%

    No Known Activations