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

    Neuronpedia

    INDEX
    Explanations

    understanding and explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     annular
    0.31
     hydrodynamic
    0.31
     securing
    0.31
     increment
    0.30
     providing
    0.30
     extrusion
    0.30
     an
    0.29
     posiada
    0.29
     DD
    0.29
     granularity
    0.29
    POSITIVE LOGITS
    understand
    0.40
    Understand
    0.40
    解释
    0.39
    essentially
    0.37
    Essentially
    0.37
     समझाया
    0.36
     explique
    0.35
    Explained
    0.35
     Understand
    0.34
     explicar
    0.34
    Act Density 0.635%

    No Known Activations