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

    Neuronpedia

    INDEX
    Explanations

    vulnerability, role, climate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     librarians
    0.46
     libraries
    0.43
     libr
    0.41
     scholastic
    0.41
     safes
    0.41
    proba
    0.40
     sensores
    0.40
     folders
    0.39
    covariance
    0.39
    ᒐ
    0.38
    POSITIVE LOGITS
    Counter
    0.39
     Lichtenfels
    0.38
    ș
    0.37
    рій
    0.37
    ome
    0.36
    ст
    0.36
     Pickup
    0.36
    Land
    0.36
     Macht
    0.36
    Browse
    0.35
    Act Density 0.000%

    No Known Activations