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

    Neuronpedia

    INDEX
    Explanations

    URL paths and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ridine
    0.43
    熹
    0.38
     comrades
    0.37
    arget
    0.36
    ilateral
    0.36
     semic
    0.36
    qdm
    0.35
     oiled
    0.35
    âce
    0.35
    ünkü
    0.35
    POSITIVE LOGITS
     Miss
    0.48
    Miss
    0.47
     amp
    0.42
     Critic
    0.41
     GOT
    0.39
     Election
    0.39
     Voting
    0.39
    -]+
    0.39
    MISS
    0.39
     Analyzer
    0.38
    Act Density 0.000%

    No Known Activations