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

    Neuronpedia

    INDEX
    Explanations

    failing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     approve
    -0.07
    characters
    -0.07
     king
    -0.06
     النو
    -0.06
     upload
    -0.06
     depict
    -0.06
     troubleshooting
    -0.06
     sharing
    -0.06
    edge
    -0.06
     国产
    -0.06
    POSITIVE LOGITS
     Es
    0.07
     mistakenly
    0.07
    /es
    0.07
    .Flow
    0.07
    Mem
    0.07
    _uniform
    0.07
    樣
    0.07
     그래
    0.07
    ere
    0.07
     DataGridViewCellStyle
    0.06
    Act Density 0.008%

    No Known Activations