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

    Neuronpedia

    INDEX
    Explanations

    beat yourself up

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    জন
    0.69
    К
    0.64
    ल
    0.63
    ু
    0.63
    ک
    0.62
    و
    0.59
    ו
    0.59
    ோ
    0.58
    হ
    0.57
    𒋼
    0.57
    POSITIVE LOGITS
     beat
    0.89
     beating
    0.86
     Beat
    0.85
     beats
    0.82
    beat
    0.82
    Beat
    0.79
    beats
    0.74
     beaten
    0.71
     Beats
    0.70
     drum
    0.60
    Act Density 0.012%

    No Known Activations