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

    Neuronpedia

    INDEX
    Explanations

    Google DeepMind

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ob
    0.68
     produse
    0.68
    款式
    0.68
     చే
    0.68
    공
    0.68
     oamen
    0.67
     விச
    0.67
    Gos
    0.66
    花园
    0.64
    經典
    0.63
    POSITIVE LOGITS
     metering
    0.65
     budgetary
    0.61
    쭌
    0.60
    듦
    0.60
     floor
    0.57
    loads
    0.56
     substrates
    0.56
    JAVADOC
    0.56
     latitude
    0.55
     attempts
    0.55
    Act Density 0.134%

    No Known Activations