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

    Neuronpedia

    INDEX
    Explanations

    section numbering

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     महीना
    0.46
    attutto
    0.42
     संवाददाता
    0.40
     blandt
    0.39
     influenz
    0.38
    ądź
    0.37
    igli
    0.37
    籲
    0.37
     Month
    0.37
    愎
    0.37
    POSITIVE LOGITS
     systems
    0.45
     samples
    0.44
    thione
    0.41
     interfaces
    0.40
     살펴보도록
    0.40
     examples
    0.40
     postulates
    0.39
    .
    0.39
     decomposition
    0.39
    Embedded
    0.38
    Act Density 0.000%

    No Known Activations