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

    Neuronpedia

    INDEX
    Explanations

    collecting leads and contact details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Spending
    0.50
     engaging
    0.45
    voting
    0.45
    x
    0.44
    estimates
    0.44
    entials
    0.44
    aux
    0.43
     पढ़कर
    0.43
    อยาก
    0.43
    itary
    0.42
    POSITIVE LOGITS
     qīng
    0.54
    Murder
    0.51
    ين
    0.50
    Floor
    0.50
     করিতেছিল
    0.49
     što
    0.48
     mě
    0.48
     kerosene
    0.47
     zert
    0.47
     karbon
    0.46
    Act Density 0.000%

    No Known Activations