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

    Neuronpedia

    INDEX
    Explanations

    euthanasia and suicide

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Horizontal
    -0.07
     sexual
    -0.07
    ится
    -0.06
     perspectives
    -0.06
    Sector
    -0.06
     pulp
    -0.06
     viral
    -0.06
    Wis
    -0.06
    поч
    -0.06
    etes
    -0.06
    POSITIVE LOGITS
    代理
    0.07
    .hidden
    0.07
    	mask
    0.07
    TouchUpInside
    0.06
     bakeka
    0.06
    =:
    0.06
    存
    0.06
    _PS
    0.06
    -paper
    0.06
    -options
    0.06
    Act Density 0.041%

    No Known Activations