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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Warm
    -0.06
    voř
    -0.06
     ROT
    -0.06
     Shame
    -0.06
     Kü
    -0.06
    _spin
    -0.06
    .Cancel
    -0.06
    malıdır
    -0.06
    washing
    -0.06
     absol
    -0.06
    POSITIVE LOGITS
    Jay
    0.08
    节点
    0.08
     BOX
    0.07
     lingerie
    0.07
    celona
    0.06
    313
    0.06
     resultat
    0.06
    (INFO
    0.06
     Προ
    0.06
     faiz
    0.06
    Act Density 0.000%

    No Known Activations