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

    Neuronpedia

    INDEX
    Explanations

    the book

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     speculations
    0.56
     말씀을
    0.52
     fermions
    0.51
     RNAs
    0.51
     marshes
    0.51
     neurons
    0.50
     condos
    0.50
     skirting
    0.50
     sulfides
    0.50
     lysates
    0.50
    POSITIVE LOGITS
    ре
    0.56
     de
    0.55
     ре
    0.49
    лятор
    0.49
     familiar
    0.46
     que
    0.46
    iger
    0.44
    這個
    0.44
     bruker
    0.44
    ení
    0.44
    Act Density 0.000%

    No Known Activations