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

    Neuronpedia

    INDEX
    Explanations

    status

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     volley
    -0.08
     Zab
    -0.08
     insults
    -0.08
     Rift
    -0.08
     insult
    -0.08
     retaliation
    -0.08
     зеркало
    -0.08
    iid
    -0.08
     Busch
    -0.07
    .divide
    -0.07
    POSITIVE LOGITS
    =status
    0.13
     statuses
    0.13
     status
    0.12
    	Status
    0.12
    (status
    0.12
     Status
    0.12
    状态
    0.12
    	status
    0.11
    Status
    0.11
    >Status
    0.11
    Act Density 0.013%

    No Known Activations