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

    Neuronpedia

    INDEX
    Explanations

    Extinguisher, engines, footprints

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Г
    0.53
    CUSSION
    0.53
    ACTION
    0.52
    verification
    0.52
     Begins
    0.52
     Verification
    0.51
     엄청
    0.51
    FTR
    0.51
     обеспечи
    0.50
     огром
    0.50
    POSITIVE LOGITS
     sitio
    0.54
     líquidos
    0.54
     frü
    0.51
     plástico
    0.51
     elb
    0.50
     fé
    0.49
    化的
    0.49
    vané
    0.47
    াসী
    0.47
     significativo
    0.47
    Act Density 0.001%

    No Known Activations