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

    Neuronpedia

    INDEX
    Explanations

    conversational abilities + prime numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gel
    0.50
    rš
    0.49
    čke
    0.48
    vyš
    0.47
     हंसी
    0.46
    használ
    0.46
    že
    0.46
    iscal
    0.46
    ké
    0.45
     невро
    0.45
    POSITIVE LOGITS
     wing
    0.47
     Paradise
    0.46
    程度の
    0.46
     v
    0.44
     cloth
    0.44
     paradise
    0.43
     worn
    0.43
     pastry
    0.43
    設備の
    0.43
    Mold
    0.42
    Act Density 0.000%

    No Known Activations