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

    Neuronpedia

    INDEX
    Explanations

    lack of trust or keys

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     필요
    0.45
                  
    0.43
    ambito
    0.43
     출연
    0.43
    occurrence
    0.43
              
    0.42
    cwnd
    0.42
    ethyl
    0.41
    always
    0.41
    election
    0.41
    POSITIVE LOGITS
     Automated
    0.52
     Albrecht
    0.50
     automated
    0.49
     Almanya
    0.46
     Nuts
    0.44
     Inter
    0.44
     ants
    0.43
     Dü
    0.43
     Tk
    0.43
     Relaxation
    0.43
    Act Density 0.004%

    No Known Activations