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

    Neuronpedia

    INDEX
    Explanations

    trespass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    사랑
    -0.06
    �
    -0.06
     능
    -0.06
     آینده
    -0.06
    것
    -0.06
     care
    -0.06
     minds
    -0.06
     oh
    -0.06
     rotational
    -0.06
    ervice
    -0.06
    POSITIVE LOGITS
     trespass
    0.14
     replen
    0.12
     NPC
    0.11
     vocabulary
    0.11
     Treasury
    0.10
     Treasurer
    0.09
    /sbin
    0.09
    sbin
    0.09
    NPC
    0.09
     ancestral
    0.09
    Act Density 0.005%

    No Known Activations