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

    Neuronpedia

    INDEX
    Explanations

    introduction and starting phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ammonium
    -0.83
     dialami
    -0.79
     coolant
    -0.78
    لك
    -0.77
     Ammonium
    -0.76
    腿
    -0.76
    anganronpa
    -0.75
    aniu
    -0.75
    Australie
    -0.74
     IPO
    -0.71
    POSITIVE LOGITS
    actionMode
    0.79
    ournal
    0.79
    OGND
    0.78
     aberto
    0.78
    ")){
    0.75
    disney
    0.74
     According
    0.74
    cursors
    0.72
     agir
    0.72
     cooking
    0.71
    Act Density 0.000%

    No Known Activations