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

    Neuronpedia

    INDEX
    Explanations

    encoded strings

    np_max-act · gemini-2.0-flash

    This neuron responds to two‐character hexadecimal byte sequences (i.e. pairs of hex digits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    اصل
    -0.07
    çek
    -0.06
    су
    -0.06
     Crist
    -0.06
     thép
    -0.06
     molt
    -0.06
    	panic
    -0.06
    нути
    -0.06
     석
    -0.06
    سنگ
    -0.06
    POSITIVE LOGITS
     Proto
    0.07
     conhe
    0.06
     income
    0.06
     bip
    0.06
     адміністратив
    0.06
     forb
    0.06
     regulates
    0.06
    	control
    0.06
     consuming
    0.06
    	before
    0.06
    Act Density 0.011%

    No Known Activations