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

    Neuronpedia

    INDEX
    Explanations

    contribute

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     виду
    -0.07
     Vancouver
    -0.06
    finder
    -0.06
    ecurity
    -0.06
    ення
    -0.06
    ستانی
    -0.06
     detained
    -0.06
    Sprite
    -0.06
     DIE
    -0.06
    oured
    -0.06
    POSITIVE LOGITS
     alright
    0.07
    _funcs
    0.07
    _wf
    0.06
    .ADD
    0.06
     setActive
    0.06
    _street
    0.06
     tamil
    0.06
     Alright
    0.06
     excavation
    0.06
    RLF
    0.06
    Act Density 0.014%

    No Known Activations