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

    Neuronpedia

    INDEX
    Explanations

    when appropriate or applicable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Potential
    0.77
    Potential
    0.74
     potenciales
    0.74
     hingegen
    0.74
     потенциа
    0.72
    之所以
    0.71
    matory
    0.68
     بينما
    0.68
     lediglich
    0.68
     ponieważ
    0.67
    POSITIVE LOGITS
     applicable
    1.71
     appropriate
    1.69
    applicable
    1.57
    appropriate
    1.47
     feasible
    1.43
     apropri
    1.41
     Appropriate
    1.41
     Applicable
    1.37
     appropri
    1.37
     warranted
    1.34
    Act Density 0.098%

    No Known Activations