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

    Neuronpedia

    INDEX
    Explanations

    religious texts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esthes
    -0.08
     stabbing
    -0.07
     Medieval
    -0.07
     Persons
    -0.07
    head
    -0.07
     EP
    -0.07
    	up
    -0.07
    _BUTTON
    -0.07
    eb
    -0.07
    Yes
    -0.07
    POSITIVE LOGITS
     TEST
    0.07
    ڄ
    0.07
     quant
    0.07
     עולה
    0.07
    _agent
    0.07
     privately
    0.07
     выполня
    0.07
    .learn
    0.07
    �
    0.07
     worlds
    0.07
    Act Density 0.035%

    No Known Activations