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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    放到
    -0.07
    tokenId
    -0.07
    ACK
    -0.07
    到达
    -0.07
    ibrated
    -0.07
    ave
    -0.07
    Brandon
    -0.07
    WARN
    -0.06
     Address
    -0.06
    	active
    -0.06
    POSITIVE LOGITS
    _STAR
    0.07
    Symbol
    0.07
    -fr
    0.07
    わり
    0.07
     güvenlik
    0.07
    śni
    0.06
    NSNotification
    0.06
     Shoes
    0.06
     המציאות
    0.06
     ölüm
    0.06
    Act Density 0.001%

    No Known Activations