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

    Neuronpedia

    INDEX
    Explanations

    741741 crisis support

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lin
    0.72
     sat
    0.69
    STOP
    0.66
     Learned
    0.66
     learned
    0.63
     safe
    0.63
     apprend
    0.63
    साय
    0.63
     Alu
    0.63
     Sat
    0.62
    POSITIVE LOGITS
    Flowers
    0.60
    far
    0.58
    Fare
    0.58
    fahrer
    0.58
    acki
    0.57
    flowers
    0.57
    fare
    0.56
    rais
    0.54
     flushing
    0.54
    fa
    0.53
    Act Density 0.247%

    No Known Activations