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

    Neuronpedia

    INDEX
    Explanations

    built from scratch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bomb
    0.38
    饌
    0.38
     Basically
    0.38
     malesuada
    0.37
     đứng
    0.37
     Stewart
    0.36
    READY
    0.36
     Arrangements
    0.36
    Secrets
    0.36
     граф
    0.36
    POSITIVE LOGITS
    ./
    0.60
    তথ্য
    0.46
    ;/
    0.45
     $/
    0.45
    "./
    0.43
    ?/
    0.43
    #/
    0.42
    nim
    0.41
    ریان
    0.40
    沧
    0.39
    Act Density 0.002%

    No Known Activations