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

    Neuronpedia

    INDEX
    Explanations

    how to find

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     moon
    0.68
     monthly
    0.67
     के
    0.67
     最
    0.62
    commitment
    0.62
     keeps
    0.61
     sets
    0.61
     every
    0.60
    \
    0.59
     what
    0.59
    POSITIVE LOGITS
     Benutz
    1.02
     instructive
    1.01
    aksanaan
    0.96
     diferite
    0.93
    acyjne
    0.93
     calorimetric
    0.90
     utenti
    0.89
    ☜
    0.89
     explanatory
    0.87
    ទ្
    0.87
    Act Density 0.003%

    No Known Activations