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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sts
    -0.06
    _BUFF
    -0.06
     윤
    -0.06
     Für
    -0.06
    publisher
    -0.06
    Artifact
    -0.06
     Sur
    -0.06
     designers
    -0.06
    terior
    -0.06
     cautioned
    -0.06
    POSITIVE LOGITS
     misuse
    0.07
     recalled
    0.07
     nghiên
    0.07
     bat
    0.06
    (layer
    0.06
    �
    0.06
     alone
    0.06
    认为
    0.06
    ็นการ
    0.06
    __)↵
    0.06
    Act Density 0.036%

    No Known Activations