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

    Neuronpedia

    INDEX
    Explanations

    yl or ethyl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	F
    -0.07
    िछ
    -0.07
     mũi
    -0.07
    _STATES
    -0.06
     civic
    -0.06
     curs
    -0.06
    .Bl
    -0.06
     Intellectual
    -0.06
     dom
    -0.06
    Birth
    -0.06
    POSITIVE LOGITS
    (detail
    0.07
     subset
    0.06
     brag
    0.06
    .filters
    0.06
    alet
    0.06
    /manage
    0.06
    _approved
    0.06
     separately
    0.06
    ertation
    0.06
     demonstr
    0.06
    Act Density 0.077%

    No Known Activations