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

    Neuronpedia

    INDEX
    Explanations

    seeking solace and meaning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Attitudes
    0.41
    multiply
    0.37
     attitudes
    0.36
     esfuer
    0.36
    態度
    0.36
     விரி
    0.36
    وندی
    0.36
     biasing
    0.35
    季
    0.35
    态度
    0.35
    POSITIVE LOGITS
     solace
    1.31
     stability
    1.04
     comfort
    0.99
     validation
    0.97
     respite
    0.94
     reassurance
    0.93
     peace
    0.93
     refuge
    0.90
     belonging
    0.89
     fulfillment
    0.88
    Act Density 0.096%

    No Known Activations