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

    Neuronpedia

    INDEX
    Explanations

    ANY

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ark
    -0.07
     Footer
    -0.07
    -0.07
     whe
    -0.07
    �合
    -0.07
    �
    -0.06
    ;left
    -0.06
     energ
    -0.06
    imb
    -0.06
     BOTH
    -0.06
    POSITIVE LOGITS
    :value
    0.07
    byname
    0.07
     магаз
    0.06
    <dd
    0.06
     metal
    0.06
     ordained
    0.06
    :CGPoint
    0.06
    (high
    0.06
    .userdetails
    0.06
    .stack
    0.06
    Act Density 0.001%

    No Known Activations