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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ecs
    -0.07
    32
    -0.06
    	ps
    -0.06
    Val
    -0.06
    ect
    -0.06
     Garden
    -0.06
    Summary
    -0.06
     Isaac
    -0.06
    Ty
    -0.06
     Feast
    -0.06
    POSITIVE LOGITS
    ốc
    0.07
     değişiklik
    0.06
    TEMPL
    0.06
     Населення
    0.06
     pollut
    0.06
    inne
    0.06
    Overrides
    0.06
     làng
    0.06
    ὰ
    0.06
     生
    0.06
    Act Density 0.075%

    No Known Activations