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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    кур
    -0.07
    insula
    -0.06
    �
    -0.06
     Brennan
    -0.06
     alarms
    -0.06
    Tmp
    -0.06
     pans
    -0.06
    -aged
    -0.06
    咲
    -0.06
     Sleeve
    -0.06
    POSITIVE LOGITS
    .oauth
    0.07
     організації
    0.07
     �
    0.06
    ("="
    0.06
     쪽
    0.06
    /mod
    0.06
     phrases
    0.06
     Ky
    0.06
    .process
    0.06
    .shared
    0.06
    Act Density 0.075%

    No Known Activations