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

    Neuronpedia

    INDEX
    Explanations

    requests

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    conto
    -0.07
    hay
    -0.07
    ktop
    -0.07
    mgr
    -0.06
    象
    -0.06
     Vulcan
    -0.06
     disgust
    -0.06
     Moment
    -0.06
    ophile
    -0.06
    691
    -0.06
    POSITIVE LOGITS
    _SPELL
    0.07
     ].
    0.07
     자동
    0.06
     проблем
    0.06
    Buff
    0.06
    	SELECT
    0.06
    _UINT
    0.06
    حص
    0.06
     testimony
    0.06
    (getClass
    0.06
    Act Density 0.046%

    No Known Activations