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

    Neuronpedia

    INDEX
    Explanations

    scary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ENDER
    -0.06
    274
    -0.06
    348
    -0.06
     disrupting
    -0.06
     methane
    -0.06
    ATYPE
    -0.06
     entrega
    -0.06
     Ψ
    -0.06
    paragus
    -0.06
    птом
    -0.06
    POSITIVE LOGITS
     scary
    0.13
     terrifying
    0.11
     frightening
    0.10
     frightened
    0.07
     Conversation
    0.07
     treasury
    0.07
     terrified
    0.07
     firepower
    0.07
     bereits
    0.06
     divorced
    0.06
    Act Density 0.010%

    No Known Activations