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

    Neuronpedia

    INDEX
    Explanations

    communication and human connection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ۔۔
    0.50
    s
    0.47
     predictor
    0.46
    esa
    0.45
     decision
    0.45
     definitely
    0.44
     c
    0.43
     it
    0.42
     Supporters
    0.42
     variável
    0.41
    POSITIVE LOGITS
    Glue
    0.60
    Leadership
    0.54
    Combined
    0.53
     ihtiy
    0.51
    Orientation
    0.51
    intervento
    0.50
    נו
    0.50
    Interruptions
    0.49
    ゴ
    0.49
    מא
    0.49
    Act Density 0.010%

    No Known Activations