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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    invitation
    -0.06
     Jeho
    -0.06
    Kansas
    -0.06
     kvinder
    -0.06
    (Packet
    -0.06
    +")
    -0.06
    /rest
    -0.06
    월부터
    -0.06
    クリ
    -0.06
    _BROWSER
    -0.06
    POSITIVE LOGITS
    	params
    0.07
     camb
    0.07
     vale
    0.07
    ्षण
    0.06
     smack
    0.06
     Scholarship
    0.06
    tober
    0.06
     creds
    0.06
     barber
    0.06
     No
    0.06
    Act Density 0.008%

    No Known Activations