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

    Neuronpedia

    INDEX
    Explanations

    creating or avoiding actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fossils
    0.50
    မဟုတ်
    0.49
     on
    0.46
    yesters
    0.46
    owler
    0.46
     eyeliner
    0.46
     transistor
    0.45
     gills
    0.45
     .
    0.44
     đức
    0.44
    POSITIVE LOGITS
     maggior
    0.46
     ikinci
    0.44
     giorno
    0.44
     venga
    0.42
     Consulta
    0.42
    rix
    0.42
    われた
    0.41
     jeunesse
    0.41
     reforzar
    0.41
     হই
    0.41
    Act Density 0.000%

    No Known Activations