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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     кв
    -0.08
    @include
    -0.07
    PROFILE
    -0.07
    igsaw
    -0.06
     Burger
    -0.06
     Strand
    -0.06
    <Course
    -0.06
     св
    -0.06
    66
    -0.06
     सच
    -0.06
    POSITIVE LOGITS
     Mare
    0.06
    ricular
    0.06
     edil
    0.06
    (top
    0.06
    (async
    0.06
    ettel
    0.06
     πολι
    0.06
    .lv
    0.06
    下来
    0.05
    (mid
    0.05
    Act Density 0.003%

    No Known Activations