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

    Neuronpedia

    INDEX
    Explanations

    frozen foods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     பண
    1.01
    Bij
    0.97
    Features
    0.96
     sand
    0.96
    ுகிற
    0.95
     sandy
    0.95
     Ralf
    0.93
    ்களை
    0.92
     Barbara
    0.92
    ்களில்
    0.91
    POSITIVE LOGITS
     expectativas
    1.07
     sorte
    0.96
     norme
    0.94
    liono
    0.94
     tarifs
    0.94
     tempos
    0.94
     supremo
    0.94
     odv
    0.94
     esperaba
    0.93
    ᴅ
    0.92
    Act Density 0.000%

    No Known Activations