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

    Neuronpedia

    INDEX
    Explanations

    second

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Genç
    -0.07
     importantes
    -0.06
    -В
    -0.06
    ôte
    -0.06
     урож
    -0.06
    ımız
    -0.06
     Roo
    -0.06
     technician
    -0.06
     культур
    -0.06
     Ně
    -0.05
    POSITIVE LOGITS
    为
    0.07
     overload
    0.06
     pregnant
    0.06
     좋은
    0.06
     goalkeeper
    0.06
     waited
    0.06
    som
    0.06
    ANCEL
    0.06
     GetString
    0.06
     contributing
    0.06
    Act Density 0.001%

    No Known Activations