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

    Neuronpedia

    INDEX
    Explanations

    finding the job you want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izards
    0.40
    зите
    0.39
    மையான
    0.39
    zić
    0.38
    вість
    0.38
    chelon
    0.38
    Fac
    0.38
    вій
    0.38
    Victor
    0.38
    Jacob
    0.37
    POSITIVE LOGITS
     libr
    0.44
    該当
    0.42
     observability
    0.41
     sajana
    0.41
     autof
    0.40
     oc
    0.38
     airborne
    0.38
     course
    0.38
     upland
    0.37
     pathMatch
    0.37
    Act Density 0.000%

    No Known Activations