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

    Neuronpedia

    INDEX
    Explanations

    fitness training

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wire
    -0.07
     国
    -0.06
     Experience
    -0.06
     minden
    -0.06
    jadi
    -0.06
    wire
    -0.06
     ViewPager
    -0.06
    duce
    -0.06
     Delicious
    -0.06
     einen
    -0.06
    POSITIVE LOGITS
     فض
    0.07
     annihil
    0.06
    oseconds
    0.06
    inesis
    0.06
    _softc
    0.06
    mir
    0.06
     {:?}",
    0.06
    осп
    0.06
    Exact
    0.06
     elems
    0.05
    Act Density 0.032%

    No Known Activations