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

    Neuronpedia

    INDEX
    Explanations

    suggest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Area
    -0.07
    	height
    -0.07
    /init
    -0.06
     noir
    -0.06
    31
    -0.06
    čný
    -0.06
    	sizeof
    -0.06
    moon
    -0.06
     counts
    -0.06
    32
    -0.06
    POSITIVE LOGITS
     suggesting
    0.13
     suggests
    0.12
     suggested
    0.12
     suggest
    0.11
     suggestive
    0.10
     suggestion
    0.08
     misguided
    0.08
    -inspired
    0.08
    gist
    0.08
    suggest
    0.07
    Act Density 0.029%

    No Known Activations