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

    Neuronpedia

    INDEX
    Explanations

    negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sign
    -0.07
    五月
    -0.06
     pitcher
    -0.06
     toddler
    -0.06
     Brooklyn
    -0.06
     guide
    -0.06
     �
    -0.06
    혼
    -0.06
     perg
    -0.06
     redo
    -0.06
    POSITIVE LOGITS
    -rounded
    0.07
    -lat
    0.07
    amble
    0.07
    /div
    0.07
    ito
    0.07
    Outlined
    0.07
    RIEND
    0.06
    :;↵
    0.06
    ा।↵
    0.06
     Axis
    0.06
    Act Density 0.033%

    No Known Activations