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

    Neuronpedia

    INDEX
    Explanations

    restriction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	DD
    -0.07
     DIR
    -0.07
     đ
    -0.06
    	row
    -0.06
    larak
    -0.06
    ))->
    -0.06
    _DIV
    -0.06
    �
    -0.06
    _DIRECT
    -0.06
    STATUS
    -0.06
    POSITIVE LOGITS
     usr
    0.07
     randomNumber
    0.07
    daughter
    0.07
     Homo
    0.07
    ayla
    0.06
     veterinarian
    0.06
     тисяч
    0.06
    лава
    0.06
     cade
    0.06
    ji
    0.06
    Act Density 0.000%

    No Known Activations