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

    Neuronpedia

    INDEX
    Explanations

    cuts and closes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Usuario
    0.54
    Tidak
    0.52
    Jumlah
    0.52
    Resource
    0.49
    Mga
    0.49
    Pyrazole
    0.48
    Imidazole
    0.48
    Choisissez
    0.48
    Questa
    0.48
    Dictionary
    0.48
    POSITIVE LOGITS
     pushed
    0.51
     ingrained
    0.51
     made
    0.50
     –
    0.49
     (
    0.48
     makes
    0.48
     over
    0.48
     often
    0.47
     like
    0.47
     revolves
    0.46
    Act Density 0.124%

    No Known Activations