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

    Neuronpedia

    INDEX
    Explanations

    free

    np_max-act · gemini-2.0-flash

    This neuron responds to occurrences of the substring “free” (as a standalone word or prefix).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    achten
    -0.07
     lúc
    -0.07
    agn
    -0.07
    (annotation
    -0.07
     illustrates
    -0.07
    Palindrome
    -0.06
     شهرستان
    -0.06
     Psychiat
    -0.06
     Chat
    -0.06
     polygon
    -0.06
    POSITIVE LOGITS
     free
    0.16
    free
    0.15
     Free
    0.14
    Free
    0.12
    -free
    0.12
     freedom
    0.11
    -Free
    0.10
     FREE
    0.10
     Freedom
    0.10
    FREE
    0.10
    Act Density 0.042%

    No Known Activations