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

    Neuronpedia

    INDEX
    Explanations

    conditional statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pawn
    -0.07
    protocol
    -0.07
    ῆς
    -0.07
    نين
    -0.06
    Crystal
    -0.06
    worth
    -0.06
    Own
    -0.06
    енным
    -0.06
    Odd
    -0.06
    メ
    -0.06
    POSITIVE LOGITS
     opatření
    0.07
     polož
    0.07
    ,buf
    0.07
     delaying
    0.06
     creds
    0.06
     topLevel
    0.06
     ук
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
    ]↵
    0.06
     wounds
    0.06
    Act Density 0.023%

    No Known Activations