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

    Neuronpedia

    INDEX
    Explanations

    (error

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vua
    -0.07
     cc
    -0.07
    	Destroy
    -0.07
    	cc
    -0.06
    .damage
    -0.06
    code
    -0.06
     Features
    -0.06
     ten
    -0.06
     constructor
    -0.06
    _memory
    -0.06
    POSITIVE LOGITS
     checkBox
    0.07
    ♡
    0.07
     Weak
    0.06
     Giving
    0.06
     Assert
    0.06
     weiter
    0.06
     {/*
    0.06
     elev
    0.06
     problematic
    0.06
    UES
    0.06
    Act Density 0.003%

    No Known Activations