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

    Neuronpedia

    INDEX
    Explanations

    collisions in games

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (selector
    -0.07
     peaceful
    -0.06
     Another
    -0.06
    valuation
    -0.06
     CFG
    -0.06
     příslu
    -0.06
     vůbec
    -0.06
    lots
    -0.06
     restau
    -0.06
     kromě
    -0.06
    POSITIVE LOGITS
    _basic
    0.07
    	ASSERT
    0.07
    caps
    0.06
     hex
    0.06
     athleticism
    0.06
    _application
    0.06
     的
    0.06
     승
    0.06
    	perror
    0.06
    ikit
    0.06
    Act Density 0.012%

    No Known Activations