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

    Neuronpedia

    INDEX
    Explanations

    operations and application

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     prostitutes
    0.57
     shameful
    0.55
     prostit
    0.51
     disrespectful
    0.51
    യ്യ
    0.49
     scandalous
    0.46
     garbage
    0.45
     counselors
    0.45
     hateful
    0.45
     fools
    0.44
    POSITIVE LOGITS
    MULT
    0.45
    NEW
    0.44
    operatively
    0.43
    应用于
    0.41
    一方面
    0.39
     اجرای
    0.39
    主动
    0.38
    automated
    0.38
    ochet
    0.38
    omechanical
    0.38
    Act Density 0.036%

    No Known Activations