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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sucker
    -0.07
    _param
    -0.06
    Jam
    -0.06
     ="
    -0.06
    ired
    -0.06
    agnostic
    -0.06
    DefaultValue
    -0.06
     جریان
    -0.06
     sim
    -0.06
     concatenated
    -0.06
    POSITIVE LOGITS
    　ヾ
    0.07
     умер
    0.07
     zih
    0.06
     Lesson
    0.06
    _SHORT
    0.06
     REPL
    0.06
    _above
    0.06
     UITextField
    0.06
    _hide
    0.06
    OPTION
    0.06
    Act Density 0.021%

    No Known Activations