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

    Neuronpedia

    INDEX
    Explanations

    assessing qualities and states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     theorem
    0.53
     di
    0.53
     Theorem
    0.50
     Fermi
    0.50
    澫
    0.49
     Strategic
    0.48
     Needs
    0.48
     Gar
    0.48
     opet
    0.47
     Financial
    0.47
    POSITIVE LOGITS
    0
    0.50
     fugitive
    0.48
    та
    0.45
    ърква
    0.44
     considérable
    0.44
    true
    0.44
    σταση
    0.43
    rage
    0.43
    েরও
    0.42
    ០
    0.42
    Act Density 0.001%

    No Known Activations