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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lines
    -0.08
     Portal
    -0.07
     jer
    -0.07
    adapt
    -0.07
    miştir
    -0.07
    敦
    -0.07
    licken
    -0.07
    то
    -0.07
     Pipe
    -0.06
     окон
    -0.06
    POSITIVE LOGITS
    .onDestroy
    0.06
    ділу
    0.06
    ancement
    0.06
    кое
    0.06
    ุตสาหกรรม
    0.06
    	Message
    0.06
    %;↵
    0.06
    poll
    0.05
     ARG
    0.05
    στρο
    0.05
    Act Density 0.001%

    No Known Activations