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

    Neuronpedia

    INDEX
    Explanations

    language specific phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vors
    0.50
     windscreen
    0.46
     Unfall
    0.46
     Bele
    0.46
     cursing
    0.45
     Bau
    0.45
     hangover
    0.44
     entsprechenden
    0.43
     Grün
    0.43
     Bamb
    0.43
    POSITIVE LOGITS
    经典的
    0.46
    abhave
    0.45
    abhavena
    0.44
    ﮨ
    0.44
    ḗ
    0.44
     jinfo
    0.43
    更大的
    0.43
    ocas
    0.43
    asambhavam
    0.43
    óln
    0.43
    Act Density 0.095%

    No Known Activations