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

    Neuronpedia

    INDEX
    Explanations

    instantiating new objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RPM
    0.45
    RPM
    0.40
    ूंगा
    0.38
    IVAL
    0.37
    NotNull
    0.36
    সঙ্গে
    0.35
    否则
    0.35
    త్రిక
    0.35
    ట్లా
    0.35
    ത്തരം
    0.35
    POSITIVE LOGITS
     御
    0.43
     všechny
    0.42
     சுகாதார
    0.37
     eventi
    0.37
     vod
    0.36
     Vod
    0.36
     wszystkie
    0.36
     generasi
    0.36
     Hernandez
    0.36
     Intelig
    0.36
    Act Density 0.000%

    No Known Activations