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

    Neuronpedia

    INDEX
    Explanations

    asking for support

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     upgraded
    -0.07
    akah
    -0.06
    XP
    -0.06
    Plant
    -0.06
    eca
    -0.06
    ungal
    -0.06
    SMS
    -0.06
    ess
    -0.06
     Ellison
    -0.06
     star
    -0.06
    POSITIVE LOGITS
     abst
    0.07
    hoa
    0.07
    νι
    0.06
     eşit
    0.06
    .DeepEqual
    0.06
    .leave
    0.06
    onomies
    0.06
    eature
    0.06
    _ENSURE
    0.06
    feb
    0.06
    Act Density 0.047%

    No Known Activations