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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    نج
    -0.07
    _GRANTED
    -0.07
    ۸
    -0.07
    ?"↵↵↵↵
    -0.06
     ύ
    -0.06
     weights
    -0.06
     cups
    -0.06
    adeon
    -0.06
    /team
    -0.06
    counts
    -0.06
    POSITIVE LOGITS
    utting
    0.06
     Playstation
    0.06
    .trace
    0.06
     MemoryStream
    0.06
     AIR
    0.06
     nakne
    0.06
    _receive
    0.06
    	NULL
    0.05
     فه
    0.05
     Fe
    0.05
    Act Density 0.001%

    No Known Activations