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

    Neuronpedia

    INDEX
    Explanations

    diff markers and file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Capt
    0.41
    throp
    0.37
     принял
    0.37
    irao
    0.37
    ことにより
    0.37
     captives
    0.36
    めて
    0.36
    Capture
    0.36
     captive
    0.36
     bones
    0.35
    POSITIVE LOGITS
     ACS
    0.40
     marge
    0.38
     MIL
    0.38
     operating
    0.38
    ự
    0.38
     skillset
    0.37
     skill
    0.37
     com
    0.37
     capability
    0.36
     unused
    0.36
    Act Density 0.000%

    No Known Activations