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

    Neuronpedia

    INDEX
    Explanations

    additional items

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    thin
    -0.07
    ату
    -0.06
    ється
    -0.06
    	explicit
    -0.06
     tela
    -0.06
     эти
    -0.06
    Thumb
    -0.06
     mesure
    -0.06
    _black
    -0.06
    　　 　
    -0.06
    POSITIVE LOGITS
    」（
    0.07
     Received
    0.07
     SIL
    0.07
     nxt
    0.07
     },{
    0.07
     العملية
    0.07
     stun
    0.07
    ุตสาห
    0.06
    -Jul
    0.06
    odel
    0.06
    Act Density 0.014%

    No Known Activations