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

    Neuronpedia

    INDEX
    Explanations

    promise scenario

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Belgium
    0.52
    Directories
    0.51
    Deposit
    0.50
    Addressing
    0.47
    Australia
    0.47
    Boot
    0.46
    Parliament
    0.45
     هیچ
    0.45
     भावनाओं
    0.45
    Manifest
    0.45
    POSITIVE LOGITS
    0
    0.46
    <0x80>
    0.45
    이스
    0.42
    টার
    0.41
     Schaus
    0.41
    ر
    0.40
     motivos
    0.40
     Peri
    0.40
     relo
    0.39
     racking
    0.39
    Act Density 0.005%

    No Known Activations