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

    Neuronpedia

    INDEX
    Explanations

    North Shore Hale Toto

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     لو
    0.39
     favours
    0.38
     ISNI
    0.36
    REFERENCE
    0.35
    istern
    0.35
     //</
    0.35
    perg
    0.34
    Reference
    0.34
     detrás
    0.34
     lurking
    0.34
    POSITIVE LOGITS
     shrimp
    0.55
     Hale
    0.52
     Turtle
    0.51
     turtles
    0.50
     turtle
    0.49
    Turtle
    0.49
    Toto
    0.48
     Sharks
    0.46
     Giovanni
    0.46
     Toto
    0.46
    Act Density 0.002%

    No Known Activations