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

    Neuronpedia

    INDEX
    Explanations

    alone

    np_max-act · gemini-2.0-flash

    This neuron detects “alone” scenarios—especially when a character is home alone with someone.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     تبد
    -0.07
    #",
    -0.06
     catal
    -0.06
    @Entity
    -0.06
    ')}}
    -0.06
     witches
    -0.06
     erfolgreich
    -0.06
     cul
    -0.06
     Martinez
    -0.05
    내기
    -0.05
    POSITIVE LOGITS
     Epidemi
    0.08
     Animated
    0.07
     phút
    0.07
     FM
    0.07
     JM
    0.06
    ?
    0.06
     desk
    0.06
     Inform
    0.06
     Somebody
    0.06
    více
    0.06
    Act Density 0.000%

    No Known Activations