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

    Neuronpedia

    INDEX
    Explanations

    chemical bonds

    np_max-act · gemini-2.0-flash

    The neuron activates on element-symbol–element-symbol tokens (like C-O, C-N, S-S, V-O, etc.), i.e. chemical bond annotations.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    жен
    -0.07
    aniel
    -0.07
    Tracking
    -0.07
    视
    -0.07
    reb
    -0.07
    ning
    -0.06
    icontrol
    -0.06
    dej
    -0.06
    746
    -0.06
    олит
    -0.06
    POSITIVE LOGITS
    .Required
    0.07
    Damage
    0.07
    (sol
    0.07
    /Instruction
    0.07
     Amendment
    0.06
    -bearing
    0.06
     PD
    0.06
     Petsc
    0.06
     Unknown
    0.06
    _triggered
    0.06
    Act Density 0.010%

    No Known Activations