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

    Neuronpedia

    INDEX
    Explanations

    toxic

    np_max-act · gemini-2.0-flash

    The neuron consistently flags terms discussing a compound’s DNA-damaging or mutation-causing risks (genotoxicity/mutagenicity).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     LP
    -0.07
     ناب
    -0.06
    lx
    -0.06
     І
    -0.06
     Thin
    -0.06
    LB
    -0.06
     XCT
    -0.06
    rani
    -0.06
    manı
    -0.05
    ophe
    -0.05
    POSITIVE LOGITS
    (dirname
    0.07
     lands
    0.07
    umble
    0.07
    (question
    0.07
    ocusing
    0.06
     Crimes
    0.06
    essed
    0.06
    	Method
    0.06
    	org
    0.06
    аци
    0.06
    Act Density 0.003%

    No Known Activations