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

    Neuronpedia

    INDEX
    Explanations

    website urls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    teman
    0.41
    iful
    0.39
    semibold
    0.39
     कोणताही
    0.39
    ott
    0.38
    randomNumber
    0.38
    params
    0.38
    larini
    0.37
     तप
    0.37
    amer
    0.36
    POSITIVE LOGITS
     CM
    0.52
     Com
    0.47
     Bz
    0.46
     COM
    0.45
     com
    0.44
     Hydra
    0.44
     Mm
    0.43
     Kom
    0.43
     Fq
    0.42
     Anakin
    0.41
    Act Density 0.009%

    No Known Activations