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

    Neuronpedia

    INDEX
    Explanations

    M

    np_max-act · gemini-2.0-flash

    This neuron activates on explicit references to self‐stimulation (e.g., the word “masturbate”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _asset
    -0.07
     kommt
    -0.06
     seminal
    -0.06
     Dome
    -0.06
     byli
    -0.06
     Sharma
    -0.06
     розум
    -0.06
    Weapon
    -0.06
    ражд
    -0.05
    스테
    -0.05
    POSITIVE LOGITS
    ynchron
    0.08
    onia
    0.07
    activ
    0.06
    فاق
    0.06
     Governor
    0.06
     marsh
    0.06
     Рез
    0.06
    mie
    0.06
    .TextView
    0.06
    ikhail
    0.06
    Act Density 0.108%

    No Known Activations