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

    Neuronpedia

    INDEX
    Explanations

    han

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    genres
    -0.08
    Comput
    -0.07
    Mission
    -0.07
     deceased
    -0.06
     associations
    -0.06
     ql
    -0.06
    	col
    -0.06
     china
    -0.06
    ites
    -0.06
     eros
    -0.06
    POSITIVE LOGITS
     abusing
    0.07
     overloaded
    0.07
     Approximately
    0.07
    adar
    0.06
     стар
    0.06
     Protector
    0.06
    .WindowManager
    0.06
    olleyError
    0.06
    alış
    0.06
    	Value
    0.06
    Act Density 0.006%

    No Known Activations