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

    Neuronpedia

    INDEX
    Explanations

    asterisk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Base
    -0.07
    :
↵
    -0.06
    _edge
    -0.06
    	y
    -0.06
     Latina
    -0.06
    Rightarrow
    -0.06
    RODUCTION
    -0.06
    _tD
    -0.06
     García
    -0.06
    とも
    -0.06
    POSITIVE LOGITS
     aktivit
    0.07
    avn
    0.06
     Prince
    0.06
     King
    0.06
     ;;↵
    0.06
     reward
    0.06
     {}),↵
    0.06
    086
    0.06
    -param
    0.06
    k
    0.06
    Act Density 0.003%

    No Known Activations