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

    Neuronpedia

    INDEX
    Explanations

    False Negative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ameras
    0.51
    Reconnect
    0.47
    yscrapers
    0.47
    )，
    0.46
    Jeremy
    0.46
     Autobiography
    0.45
     fonbet
    0.45
    sser
    0.44
    ்கலை
    0.43
    ethoven
    0.43
    POSITIVE LOGITS
     latex
    0.50
     fl
    0.47
     rubber
    0.47
    ة
    0.46
     hanging
    0.44
    inhib
    0.43
     strait
    0.43
     flip
    0.43
     bracket
    0.43
    ர்களில்
    0.43
    Act Density 0.001%

    No Known Activations