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

    Neuronpedia

    INDEX
    Explanations

    average

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nip
    -0.07
     MATCH
    -0.06
     立
    -0.06
     krb
    -0.06
    igor
    -0.06
     Agility
    -0.06
     cev
    -0.06
     Vibr
    -0.06
    Variable
    -0.06
     acceler
    -0.06
    POSITIVE LOGITS
    ульта
    0.07
    adge
    0.07
     konci
    0.07
    _FRAGMENT
    0.06
    шим
    0.06
    argins
    0.06
    СР
    0.06
     Doctors
    0.06
     createStore
    0.06
     совет
    0.06
    Act Density 0.019%

    No Known Activations