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

    Neuronpedia

    INDEX
    Explanations

    Theresa

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    diği
    -0.08
    �
    -0.07
    瘤
    -0.07
     sucker
    -0.07
    שק
    -0.07
    itten
    -0.07
    装备
    -0.06
    ượng
    -0.06
     risking
    -0.06
    y
    -0.06
    POSITIVE LOGITS
    _trans
    0.07
     tempo
    0.07
    _REMOVE
    0.07
    מדיניות
    0.07
    Thought
    0.07
    \Field
    0.07
     enclave
    0.06
    Advertisements
    0.06
     holidays
    0.06
     boats
    0.06
    Act Density 0.001%

    No Known Activations