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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    deme
    -0.07
     فرزند
    -0.07
    нять
    -0.06
    μάτων
    -0.06
    ителей
    -0.06
    erties
    -0.06
     reputed
    -0.06
    ня
    -0.06
    .entities
    -0.06
    coop
    -0.06
    POSITIVE LOGITS
    (comm
    0.07
    )object
    0.07
     suspicion
    0.07
    (max
    0.07
    –
    0.07
     onCreateViewHolder
    0.06
     Spirit
    0.06
     rejection
    0.06
    Transport
    0.06
     Scho
    0.06
    Act Density 0.001%

    No Known Activations