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

    Neuronpedia

    INDEX
    Explanations

    antivirus executable or symbolic notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    older
    0.51
     используются
    0.49
    arendon
    0.49
     competencias
    0.49
     наблюда
    0.47
     antiguos
    0.46
    ढ़
    0.46
    owers
    0.45
    clesi
    0.45
     utilizadas
    0.45
    POSITIVE LOGITS
     Coming
    0.52
     Scop
    0.50
     iPhone
    0.48
     Zusammen
    0.47
     Ever
    0.47
     Like
    0.46
     vehement
    0.45
     Rig
    0.45
     \
    0.45
     Thr
    0.45
    Act Density 0.000%

    No Known Activations