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

    Neuronpedia

    INDEX
    Explanations

    invitations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    χρι
    -0.07
     Atlanta
    -0.07
    vtColor
    -0.06
    .getLocation
    -0.06
     CONSEQUENTIAL
    -0.06
     Từ
    -0.06
     collapse
    -0.06
     �
    -0.06
     cavern
    -0.06
     submarines
    -0.06
    POSITIVE LOGITS
     captivating
    0.06
    _STOP
    0.06
     joining
    0.06
    mem
    0.06
     FOOT
    0.06
     Adopt
    0.06
     Double
    0.06
     니
    0.06
     우리는
    0.06
     combine
    0.06
    Act Density 0.014%

    No Known Activations