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

    Neuronpedia

    INDEX
    Explanations

    toggle

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	pl
    -0.07
     prisoners
    -0.07
    .Skip
    -0.07
     Ricky
    -0.06
     bur
    -0.06
     Father
    -0.06
     Enemies
    -0.06
     khí
    -0.06
    -ft
    -0.06
     enr
    -0.06
    POSITIVE LOGITS
    toggle
    0.09
    -toggle
    0.08
     toggle
    0.08
    Tok
    0.07
    teg
    0.07
    _toggle
    0.07
    Toggle
    0.07
     Toggle
    0.07
    )])↵↵
    0.07
    .toggle
    0.07
    Act Density 0.003%

    No Known Activations