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

    Neuronpedia

    INDEX
    Explanations

    Raw Materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     at
    0.52
    해서
    0.51
    (
    0.46
     ailments
    0.45
    hai
    0.44
    hesi
    0.44
    내
    0.43
     à
    0.43
     largely
    0.43
     is
    0.43
    POSITIVE LOGITS
     Smyrna
    0.51
    берг
    0.49
     Oldborough
    0.49
     बीटल
    0.49
    ંપની
    0.49
    лександр
    0.49
     INumber
    0.48
    噔
    0.48
    IVATE
    0.47
     Yn
    0.47
    Act Density 0.001%

    No Known Activations