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

    Neuronpedia

    INDEX
    Explanations

    data labels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    appy
    -0.07
     Interest
    -0.07
     Spirit
    -0.07
     Pressure
    -0.07
     коли
    -0.06
     ranked
    -0.06
     through
    -0.06
     NORTH
    -0.06
    ]]
↵
    -0.06
     heavy
    -0.06
    POSITIVE LOGITS
    �
    0.06
    λο
    0.06
     표현
    0.06
     υπάρχ
    0.06
    <Texture
    0.06
    支援
    0.06
    <Message
    0.06
    _enqueue
    0.06
    deş
    0.06
    .GetMapping
    0.06
    Act Density 0.007%

    No Known Activations