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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    抗击
    -0.07
    ;charset
    -0.07
    ו�
    -0.06
    瘐
    -0.06
    翾
    -0.06
    chen
    -0.06
     defaultProps
    -0.06
    俵
    -0.06
    打动
    -0.06
    𝘠
    -0.06
    POSITIVE LOGITS
     SCC
    0.08
     dedicated
    0.07
     minimise
    0.07
     Elliott
    0.07
     תמיד
    0.07
     wikipedia
    0.07
     Certainly
    0.07
    Previously
    0.07
    ERTICAL
    0.06
    开户
    0.06
    Act Density 0.039%

    No Known Activations