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

    Neuronpedia

    INDEX
    Explanations

    individual response components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    acterial
    0.54
    adari
    0.48
    createNew
    0.48
    onnen
    0.47
    çok
    0.46
    ennzeichnet
    0.46
    known
    0.44
    apeutic
    0.44
     विविध
    0.44
    রাজনৈতিক
    0.44
    POSITIVE LOGITS
     spectra
    0.44
     parts
    0.42
     segments
    0.42
     panels
    0.41
     things
    0.41
     isotopes
    0.40
     batches
    0.40
     section
    0.40
     groups
    0.40
     cards
    0.40
    Act Density 0.107%

    No Known Activations