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

    Neuronpedia

    INDEX
    Explanations

    needs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rl
    -0.07
    FOUNDATION
    -0.06
     prox
    -0.06
     Supporting
    -0.06
    ��
    -0.06
     apprent
    -0.06
    nThe
    -0.06
     Yug
    -0.06
     governance
    -0.06
     insights
    -0.06
    POSITIVE LOGITS
     شكل
    0.07
    _fonts
    0.06
    –
    0.06
    俄
    0.06
    ड
    0.06
    -thirds
    0.06
    .consumer
    0.06
     Ramos
    0.06
    hero
    0.06
                    
    0.06
    Act Density 0.010%

    No Known Activations