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

    Neuronpedia

    INDEX
    Explanations

    concerns regarding data deletion and recovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    confirm deletion or recovery

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itſelf
    -0.57
    ſelves
    -0.56
    endmodule
    -0.55
     myſelf
    -0.55
    锈钢
    -0.53
     uſe
    -0.52
     Efq
    -0.50
     fevere
    -0.50
    neſs
    -0.48
    ſelf
    -0.48
    POSITIVE LOGITS
    mybatisplus
    0.55
    onDelete
    0.45
    OnDelete
    0.40
    DeleteMapping
    0.37
     confirmation
    0.37
     ***!
    0.36
    confirm
    0.35
    RTSC
    0.35
    flashdata
    0.35
    confirmButton
    0.35
    Act Density 0.108%

    No Known Activations