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

    Neuronpedia

    INDEX
    Explanations

    Physical appearance and sexuality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     menace
    -0.07
    �로
    -0.06
    	damage
    -0.06
    OV
    -0.06
     ]]↵
    -0.06
     Dialogue
    -0.06
    continental
    -0.06
    obs
    -0.06
     nationalists
    -0.06
    ankind
    -0.06
    POSITIVE LOGITS
     backbone
    0.07
     txt
    0.07
    [Byte
    0.07
    cts
    0.07
    avigator
    0.07
    壓
    0.06
     ratios
    0.06
    _UNDEF
    0.06
    481
    0.06
    ーチ
    0.06
    Act Density 0.002%

    No Known Activations