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

    Neuronpedia

    INDEX
    Explanations

    trigger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Assembler
    -0.08
     oxide
    -0.07
    mant
    -0.07
     notation
    -0.07
     odpowied
    -0.06
     EAST
    -0.06
    �
    -0.06
    asant
    -0.06
     Apartments
    -0.06
     homeland
    -0.06
    POSITIVE LOGITS
     trigger
    0.18
     triggering
    0.15
    trigger
    0.14
     Trigger
    0.14
     triggers
    0.14
     triggered
    0.13
    Trigger
    0.12
    _trigger
    0.11
    -trigger
    0.10
    .trigger
    0.09
    Act Density 0.008%

    No Known Activations