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

    Neuronpedia

    INDEX
    Explanations

    Scala and its applications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Emergency
    0.40
     podremos
    0.39
     abdomen
    0.39
    र्मा
    0.38
     marching
    0.37
    undred
    0.37
     Pam
    0.37
     determine
    0.36
    ιουργ
    0.36
     Sah
    0.36
    POSITIVE LOGITS
    Scala
    1.61
     Scala
    1.53
     scala
    1.36
    scala
    1.34
    scal
    0.96
    Scal
    0.95
     scal
    0.93
    akka
    0.84
     akka
    0.82
     Scal
    0.79
    Act Density 0.003%

    No Known Activations