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

    Neuronpedia

    INDEX
    Explanations

    personal reflections and expressions of experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    conjunctions then verbs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الرياضيه
    -0.49
    SizeMode
    -0.46
    balleur
    -0.43
     تضيفلها
    -0.41
     femininas
    -0.41
     Demokratie
    -0.40
     MaterialApp
    -0.39
     bluzka
    -0.39
     AspNetCore
    -0.39
    Portale
    -0.38
    POSITIVE LOGITS
    Bind
    0.47
     '{@
    0.46
     anſ
    0.45
     LUMP
    0.44
     AMP
    0.42
    ſtre
    0.42
     Cele
    0.42
    ativement
    0.41
    anguages
    0.40
    /***/
    0.40
    Act Density 0.060%

    No Known Activations