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

    Neuronpedia

    INDEX
    Explanations

    technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Animator
    -0.08
     identical
    -0.08
    的表情
    -0.08
    -done
    -0.08
    kubectl
    -0.07
    /status
    -0.07
    _assign
    -0.07
    一双
    -0.07
     distinctly
    -0.07
    一片
    -0.07
    POSITIVE LOGITS
    .Flag
    0.07
    ᥣ
    0.07
     ''
↵
    0.06
     lithium
    0.06
     ench
    0.06
    ��
    0.06
    𬕂
    0.06
     ''↵
    0.06
     ResourceType
    0.06
    깞
    0.06
    Act Density 0.107%

    No Known Activations