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

    Neuronpedia

    INDEX
    Explanations

    discussions and responses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     금
    -0.07
     документів
    -0.06
     γρα
    -0.06
    Matchers
    -0.06
    	ns
    -0.06
    -es
    -0.06
    /ca
    -0.06
     مذه
    -0.06
     NGO
    -0.06
     цін
    -0.06
    POSITIVE LOGITS
     spike
    0.07
     lately
    0.07
     killed
    0.07
    Value
    0.06
     Ağustos
    0.06
     dw
    0.06
     copied
    0.06
    VERBOSE
    0.06
    ready
    0.06
    ]?
    0.06
    Act Density 0.000%

    No Known Activations