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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .lastname
    -0.06
     Paths
    -0.06
     firmly
    -0.06
     Sun
    -0.06
     ホ
    -0.06
    sources
    -0.06
     самое
    -0.06
     输入
    -0.06
     speaks
    -0.06
    类型
    -0.06
    POSITIVE LOGITS
     ()=>{↵
    0.07
     kills
    0.07
    .inflate
    0.07
    -kit
    0.07
     mature
    0.06
     obesity
    0.06
     assessing
    0.06
     kg
    0.06
     Acid
    0.06
    )=>{↵
    0.06
    Act Density 0.000%

    No Known Activations