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

    Neuronpedia

    INDEX
    Explanations

    figure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    knowledge
    -0.07
    ptive
    -0.07
    ота
    -0.07
     cooler
    -0.07
     عکس
    -0.07
    ته
    -0.07
    (content
    -0.06
     banning
    -0.06
    cts
    -0.06
     Іван
    -0.06
    POSITIVE LOGITS
     contaminants
    0.07
    )):
↵
    0.06
    _Selected
    0.06
    	TRACE
    0.06
     Dat
    0.06
    _rwlock
    0.06
     Rem
    0.05
    _inc
    0.05
     Sı
    0.05
    _asm
    0.05
    Act Density 0.035%

    No Known Activations