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

    Neuronpedia

    INDEX
    Explanations

    tools

    np_max-act · gemini-2.0-flash

    The neuron detects occurrences of the word “tools.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .badlogic
    -0.07
    Bubble
    -0.07
    	cpu
    -0.06
     german
    -0.06
     Dim
    -0.06
    (test
    -0.06
     Minuten
    -0.06
    (Random
    -0.06
    سبب
    -0.06
     copyright
    -0.06
    POSITIVE LOGITS
     ngOnInit
    0.06
    راف
    0.06
     valida
    0.06
     reel
    0.06
     Prostitutas
    0.06
    isión
    0.06
     fiercely
    0.06
     Pollution
    0.06
     plaats
    0.06
    anie
    0.06
    Act Density 0.051%

    No Known Activations