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

    Neuronpedia

    INDEX
    Explanations

    who + they

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    B
    0.45
    Slack
    0.43
    _{+
    0.42
    Light
    0.42
    平台
    0.42
     бар
    0.41
    Ra
    0.41
     plateau
    0.41
    Platform
    0.41
    学习
    0.41
    POSITIVE LOGITS
    necess
    0.46
    ributions
    0.46
     liable
    0.44
    chek
    0.43
     दूं
    0.43
    phil
    0.42
    ilikom
    0.42
     necess
    0.42
    dez
    0.42
    innov
    0.42
    Act Density 0.010%

    No Known Activations