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

    Neuronpedia

    INDEX
    Explanations

    CV

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.08
    asiswa
    -0.07
    晌
    -0.07
    ᠩ
    -0.07
    Ǎ
    -0.07
    _resolve
    -0.06
     recruiter
    -0.06
    猜测
    -0.06
    pla
    -0.06
    isto
    -0.06
    POSITIVE LOGITS
    project
    0.07
    Title
    0.07
    _load
    0.07
    还原
    0.07
     Night
    0.06
     Crime
    0.06
    服务
    0.06
     Built
    0.06
    .Then
    0.06
    Mother
    0.06
    Act Density 0.001%

    No Known Activations