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

    Neuronpedia

    INDEX
    Explanations

    claim

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    洄
    -0.07
    鹳
    -0.07
    룻
    -0.07
    .FormattingEnabled
    -0.07
    .Abs
    -0.07
    蒗
    -0.07
    anoi
    -0.07
    现实中
    -0.07
    ἀ
    -0.07
     Comparative
    -0.07
    POSITIVE LOGITS
    ꌼ
    0.07
    (embed
    0.07
    recogn
    0.07
    ############################################################
    0.06
     Assoc
    0.06
     làm
    0.06
     matéria
    0.06
    FH
    0.06
    reg
    0.06
    举
    0.06
    Act Density 0.024%

    No Known Activations