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

    Neuronpedia

    INDEX
    Explanations

    email/url signatures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᗩ
    -0.08
     synt
    -0.07
    蓝色
    -0.07
    פורום
    -0.07
     actors
    -0.07
     TableName
    -0.07
    apikey
    -0.07
     anesthesia
    -0.07
    𝘶
    -0.07
     halluc
    -0.06
    POSITIVE LOGITS
    _REMOVE
    0.07
    艏
    0.07
    ߦ
    0.07
    积淀
    0.07
    腯
    0.06
    脿
    0.06
     retains
    0.06
     succeeding
    0.06
    �
    0.06
    .loaded
    0.06
    Act Density 0.005%

    No Known Activations