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

    Neuronpedia

    INDEX
    Explanations

    deliberate tactic showed stir

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сто
    0.39
     Giving
    0.39
     🙌
    0.38
     Santo
    0.38
     कह
    0.38
     kicking
    0.37
    ǽ
    0.37
    ﻑ
    0.37
     अनुमति
    0.36
     giving
    0.36
    POSITIVE LOGITS
    Rio
    0.40
    Tested
    0.37
    Princeton
    0.37
    Czech
    0.37
    Primary
    0.37
    vit
    0.36
    Juan
    0.35
    Corporate
    0.35
    Rick
    0.35
    primary
    0.35
    Act Density 0.000%

    No Known Activations