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

    Neuronpedia

    INDEX
    Explanations

    9

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Store
    -0.08
     flipped
    -0.07
     explodes
    -0.07
     abused
    -0.06
     thinks
    -0.06
    щим
    -0.06
     acquisition
    -0.06
     statistic
    -0.06
     vod
    -0.06
    ({↵↵
    -0.06
    POSITIVE LOGITS
    _pci
    0.07
    �
    0.07
     انواع
    0.06
    (ir
    0.06
    )":
    0.06
     сы
    0.06
     ří
    0.06
     rov
    0.06
     ImVec
    0.06
     homemade
    0.06
    Act Density 0.011%

    No Known Activations