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

    Neuronpedia

    INDEX
    Explanations

    xml namespaces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     what
    -1.20
     isolada
    -1.12
    moine
    -1.07
    roaches
    -1.06
     baratas
    -1.05
     confuso
    -1.03
    $.}
    -1.02
     miesięcy
    -1.01
     trying
    -0.98
    無し
    -0.98
    POSITIVE LOGITS
    u
    1.39
    chi
    1.30
    ya
    1.27
    op
    1.27
    zz
    1.24
    us
    1.24
    oo
    1.23
    z
    1.23
    ii
    1.23
    ss
    1.22
    Act Density 0.001%

    No Known Activations