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

    Neuronpedia

    INDEX
    Explanations

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    queryParams
    -0.07
    ju
    -0.07
    ivic
    -0.07
     campos
    -0.07
    appings
    -0.06
    aks
    -0.06
     tj
    -0.06
    eming
    -0.06
     Tiles
    -0.06
     jewels
    -0.06
    POSITIVE LOGITS
     discount
    0.07
    见过
    0.07
     gotta
    0.07
    亲眼
    0.07
     gratuite
    0.07
    ถ
    0.07
    ASSWORD
    0.06
     đóng
    0.06
    .must
    0.06
    脱发
    0.06
    Act Density 0.145%

    No Known Activations