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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     เซ
    -0.07
    ffee
    -0.07
     predator
    -0.06
    users
    -0.06
    eni
    -0.06
     самый
    -0.06
    akov
    -0.06
     cunning
    -0.06
    sap
    -0.06
    σετε
    -0.06
    POSITIVE LOGITS
    "?↵↵
    0.07
     softened
    0.06
    (O
    0.06
     orientations
    0.06
     containment
    0.06
    _IMP
    0.06
     trolls
    0.06
     jpeg
    0.06
    +N
    0.06
     IPC
    0.06
    Act Density 0.005%

    No Known Activations