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

    Neuronpedia

    INDEX
    Explanations

    principal investment design code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    an
    0.61
    le
    0.57
     The
    0.50
    a
    0.46
    he
    0.46
    The
    0.46
    the
    0.45
    ina
    0.44
    ich
    0.43
    one
    0.42
    POSITIVE LOGITS
    mselves
    0.38
     entire
    0.38
     desired
    0.38
    odore
    0.36
     expanse
    0.36
     entirety
    0.36
    ０
    0.36
     original
    0.36
     foundations
    0.36
     hottest
    0.35
    Act Density 0.000%

    No Known Activations