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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    %'
    -0.07
    ี
    -0.07
    “And
    -0.07
    .%
    -0.07
    _%
    -0.07
     ένα
    -0.06
    +#
    -0.06
    _NT
    -0.06
    X
    -0.06
    _ARR
    -0.06
    POSITIVE LOGITS
    (m
    0.20
    (p
    0.18
    (h
    0.17
    (g
    0.16
    (d
    0.15
    (v
    0.14
    (w
    0.14
    (c
    0.13
    (l
    0.13
    (j
    0.12
    Act Density 0.043%

    No Known Activations