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

    Neuronpedia

    INDEX
    Explanations

    Memoir prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     चले
    -0.08
     Dangerous
    -0.08
     Егер
    -0.08
     सुविध
    -0.08
     nasty
    -0.08
     ДТП
    -0.08
     �
    -0.08
    izeit
    -0.08
    айтесь
    -0.08
     автобус
    -0.08
    POSITIVE LOGITS
     resilience
    0.10
     humility
    0.09
     patience
    0.09
     mindfulness
    0.08
     kindness
    0.08
     believing
    0.08
     puzzle
    0.08
     tapestry
    0.08
     compassion
    0.08
    deb
    0.07
    Act Density 0.028%

    No Known Activations