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

    Neuronpedia

    INDEX
    Explanations

    needing money or standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    final
    -0.07
    xito
    -0.06
    콩
    -0.06
    ポ
    -0.06
    白
    -0.06
    一切
    -0.06
     hills
    -0.06
    ispecies
    -0.06
    urst
    -0.06
     Partnership
    -0.06
    POSITIVE LOGITS
    (mp
    0.07
     earns
    0.06
     excav
    0.06
    {|
    0.06
     SIMPLE
    0.06
    Witness
    0.06
     entrances
    0.06
    .firstname
    0.06
    =z
    0.06
    |:
    0.06
    Act Density 0.169%

    No Known Activations