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

    Neuronpedia

    INDEX
    Explanations

    explaining what something is about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     बखूबी
    0.37
    éhez
    0.34
    翕
    0.34
     cunoscut
    0.34
     совершен
    0.33
    ≃
    0.33
    ady
    0.33
    esehatan
    0.32
     извест
    0.32
     breached
    0.32
    POSITIVE LOGITS
     blueberry
    0.38
     adaptation
    0.38
     logging
    0.37
     about
    0.37
     preferring
    0.37
     sorting
    0.35
    payment
    0.35
     potting
    0.35
     rejection
    0.34
     putting
    0.34
    Act Density 0.077%

    No Known Activations