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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     동
    -0.07
    _leg
    -0.07
    preferred
    -0.06
    Compra
    -0.06
    	T
    -0.06
     mount
    -0.06
     Salmon
    -0.06
    gL
    -0.06
     FORWARD
    -0.06
    Um
    -0.06
    POSITIVE LOGITS
    @register
    0.07
     slaughter
    0.07
    orman
    0.06
    âl
    0.06
     receives
    0.06
    .TextUtils
    0.06
    .scalar
    0.06
     targeting
    0.06
     Appeals
    0.06
    iteur
    0.06
    Act Density 0.097%

    No Known Activations