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

    Neuronpedia

    INDEX
    Explanations

    follows your recommendation or molecule can cleave

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     suminist
    0.55
     desple
    0.52
     químico
    0.52
     прив
    0.52
    óloga
    0.52
    쟤
    0.52
     limpieza
    0.51
     receta
    0.51
     সঠিক
    0.50
     enregist
    0.50
    POSITIVE LOGITS
    a
    0.51
    ia
    0.51
     a
    0.50
    o
    0.49
    高
    0.48
    ha
    0.45
    P
    0.45
    man
    0.44
    ad
    0.44
     as
    0.44
    Act Density 0.000%

    No Known Activations