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

    Neuronpedia

    INDEX
    Explanations

    common phrase beginnings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Security
    0.32
     potable
    0.32
     technologies
    0.31
     Biological
    0.31
     bathing
    0.31
     水
    0.30
     ecosystems
    0.30
     Technologies
    0.30
     lithium
    0.30
     semiconductor
    0.30
    POSITIVE LOGITS
    ш
    0.39
     crusade
    0.38
    стра
    0.38
     outspoken
    0.38
    ן
    0.37
    ൭
    0.37
    ਨ
    0.36
    к
    0.36
    ਟ
    0.35
    на
    0.35
    Act Density 1.586%

    No Known Activations