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

    Neuronpedia

    INDEX
    Explanations

    recognize

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    72
    -0.08
    12
    -0.08
     east
    -0.07
    582
    -0.07
     freezing
    -0.07
     dB
    -0.07
    /json
    -0.07
    778
    -0.06
    _MINUS
    -0.06
    ²
    -0.06
    POSITIVE LOGITS
     recognize
    0.13
     recognizing
    0.13
     recognized
    0.11
     recognizes
    0.11
     recognise
    0.10
     Recogn
    0.09
     recognizer
    0.09
     recognised
    0.08
    зн
    0.08
    Recognizer
    0.08
    Act Density 0.022%

    No Known Activations