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

    Neuronpedia

    INDEX
    Explanations

    recalls and refunds

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     mädchen
    -0.07
     الأم
    -0.07
    ⇔
    -0.07
    ION
    -0.07
     Ukraine
    -0.07
    ion
    -0.07
    .Autowired
    -0.07
    曼联
    -0.07
    -pound
    -0.06
    POSITIVE LOGITS
     lucky
    0.07
     basics
    0.07
     beware
    0.07
    收藏
    0.07
    岭南
    0.07
     locating
    0.07
     specialization
    0.06
    acic
    0.06
     popularity
    0.06
    lectic
    0.06
    Act Density 0.053%

    No Known Activations