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

    Neuronpedia

    INDEX
    Explanations

    cults

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kicks
    -0.06
    .in
    -0.06
    Wy
    -0.06
     further
    -0.06
    μείο
    -0.06
    番号
    -0.06
    .op
    -0.06
    委员
    -0.06
    르
    -0.06
     Watts
    -0.06
    POSITIVE LOGITS
     published
    0.07
     Dumpster
    0.07
     spyOn
    0.07
    něm
    0.06
    liked
    0.06
     inhabited
    0.06
     purchased
    0.06
     qualité
    0.06
     limitations
    0.06
    Previously
    0.06
    Act Density 0.014%

    No Known Activations