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

    Neuronpedia

    INDEX
    Explanations

    vase

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     گی
    -0.07
    ्त
    -0.07
    andbox
    -0.06
    ampton
    -0.06
    acoes
    -0.06
     predators
    -0.06
     Protein
    -0.06
     mafia
    -0.06
    alysis
    -0.06
     shred
    -0.06
    POSITIVE LOGITS
     vase
    0.13
     pitcher
    0.07
    ệnh
    0.07
     ΑΓ
    0.07
    زینه
    0.07
     Vick
    0.07
    州
    0.07
    annon
    0.06
     görev
    0.06
    佩
    0.06
    Act Density 0.006%

    No Known Activations