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

    Neuronpedia

    INDEX
    Explanations

    point

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fib
    -0.08
     looming
    -0.07
    IB
    -0.07
     suicide
    -0.07
    software
    -0.07
     coordination
    -0.07
    -Free
    -0.06
     tren
    -0.06
     Pane
    -0.06
    Govern
    -0.06
    POSITIVE LOGITS
     schvál
    0.07
     crear
    0.07
    _));↵
    0.06
    reau
    0.06
    255
    0.06
    elerde
    0.06
    ')),↵
    0.06
     AppState
    0.06
     requesting
    0.06
    	create
    0.06
    Act Density 0.014%

    No Known Activations