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

    Neuronpedia

    INDEX
    Explanations

    and,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Pearce
    -0.07
     Lease
    -0.07
    关系
    -0.07
    (Level
    -0.07
     işlem
    -0.06
     gyro
    -0.06
     disgusting
    -0.06
    .jet
    -0.06
     pact
    -0.06
    uffers
    -0.06
    POSITIVE LOGITS
    _
    0.06
    _SEGMENT
    0.06
     Ð
    0.06
     industrial
    0.06
    ANCES
    0.06
    alleries
    0.06
    subtitle
    0.06
    ffi
    0.06
    ستگی
    0.06
     tématu
    0.06
    Act Density 0.067%

    No Known Activations