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

    Neuronpedia

    INDEX
    Explanations

    physical states and changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ene
    0.59
    laptop
    0.55
    ogn
    0.49
    0.49
     الاسم
    0.48
    lim
    0.48
    np
    0.47
    ක්
    0.47
    z
    0.47
    lj
    0.46
    POSITIVE LOGITS
    }:=\
    0.51
     beerCount
    0.47
     uitgenodigd
    0.46
     Gurgaon
    0.45
     paciente
    0.45
    接著
    0.45
     Anbieter
    0.45
    лянчук
    0.44
    ometries
    0.44
     tempering
    0.44
    Act Density 0.000%

    No Known Activations