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

    Neuronpedia

    INDEX
    Explanations

    ahas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eriod
    -0.07
     investment
    -0.07
     televis
    -0.06
     sandwiches
    -0.06
     Linked
    -0.06
    iostream
    -0.06
    Wide
    -0.06
     wizards
    -0.06
     Noticed
    -0.06
     homicide
    -0.06
    POSITIVE LOGITS
     �
    0.07
    PCS
    0.06
     Yad
    0.06
     Laur
    0.06
    ывал
    0.06
    rf
    0.06
    ίου
    0.06
     że
    0.06
     Fol
    0.06
    ματος
    0.06
    Act Density 0.001%

    No Known Activations