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

    Neuronpedia

    INDEX
    Explanations

    technical specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prevailed
    -0.07
     trying
    -0.06
     analyze
    -0.06
     Spiele
    -0.06
    umbn
    -0.06
     NOTHING
    -0.06
     Myers
    -0.06
     Yad
    -0.06
     Ham
    -0.06
     зараз
    -0.06
    POSITIVE LOGITS
    _TESTS
    0.07
     certificates
    0.07
    _PROCESS
    0.07
    +',
    0.07
    faction
    0.06
    hattan
    0.06
    .restart
    0.06
    (tokens
    0.06
    .apps
    0.06
    .Mode
    0.06
    Act Density 0.185%

    No Known Activations