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

    Neuronpedia

    INDEX
    Explanations

    first, guard, steps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    abri
    0.45
     hadrons
    0.43
     bullies
    0.42
     Gerrard
    0.42
     protons
    0.42
    ubis
    0.42
    Griff
    0.41
     resolvers
    0.41
     Griffiths
    0.41
    ab
    0.40
    POSITIVE LOGITS
    える
    0.51
    }.
    0.46
     nuove
    0.44
     trái
    0.43
    bagian
    0.43
     trên
    0.43
    }};
    0.42
     .
    0.42
     nuovi
    0.42
     toán
    0.42
    Act Density 0.005%

    No Known Activations