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

    Neuronpedia

    INDEX
    Explanations

    hats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     onCreateView
    -0.50
    UTC
    -0.44
    tabil
    -0.41
     Catawiki
    -0.41
    TestingModule
    -0.41
    zept
    -0.40
     Verantwort
    -0.40
     responsab
    -0.40
    Aktu
    -0.40
     melh
    -0.40
    POSITIVE LOGITS
    gered
    0.75
    enumii
    0.66
    OGND
    0.66
     becauſe
    0.63
    glers
    0.63
    رشف
    0.58
    gly
    0.57
     Theſe
    0.57
     vests
    0.57
     ſhe
    0.57
    Act Density 0.009%

    No Known Activations