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

    Neuronpedia

    INDEX
    Explanations

    Monster

    np_max-act · gemini-2.0-flash

    The neuron activates primarily on the word “Monster,” especially when used as a headline or title token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Painting
    -0.08
    �
    -0.07
     Faculty
    -0.07
     circum
    -0.07
     Catherine
    -0.07
     Geb
    -0.07
     Communication
    -0.07
     Dou
    -0.07
     अव
    -0.06
     Cou
    -0.06
    POSITIVE LOGITS
     monster
    0.13
     monsters
    0.09
     Monsters
    0.09
     disasters
    0.09
     Monster
    0.09
     disaster
    0.08
     Beast
    0.08
    MAN
    0.08
     beast
    0.08
    Monster
    0.08
    Act Density 0.006%

    No Known Activations