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

    Neuronpedia

    INDEX
    Explanations

    rules, schemes, spin-offs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kola
    0.40
    ~~~~
    0.39
    ~~~~~~~~
    0.38
    ꒦
    0.38
    飧
    0.38
    🏞
    0.38
     moor
    0.37
    𝄞
    0.37
     आखिर
    0.37
    🥢
    0.37
    POSITIVE LOGITS
    izz
    0.50
     hypothesis
    0.47
     hypotheses
    0.43
     Mall
    0.43
    ulan
    0.40
     signalling
    0.39
     recruit
    0.38
    isu
    0.38
     áreas
    0.38
    arden
    0.37
    Act Density 0.000%

    No Known Activations