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

    Neuronpedia

    INDEX
    Explanations

    real

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bag
    -0.06
     Jack
    -0.06
    BufferData
    -0.06
     Carson
    -0.06
     Samantha
    -0.06
     Chi
    -0.06
     heuristic
    -0.06
    334
    -0.06
     PDT
    -0.06
    -hook
    -0.05
    POSITIVE LOGITS
    rego
    0.07
     cosplay
    0.07
     recipient
    0.07
     FormBuilder
    0.07
    cold
    0.06
     accessible
    0.06
     niveau
    0.06
     Unfortunately
    0.06
     impressed
    0.06
    	info
    0.06
    Act Density 0.006%

    No Known Activations