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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (in
    -0.07
    िट
    -0.07
     primarily
    -0.07
    =h
    -0.06
    122
    -0.06
     glacier
    -0.06
    انگ
    -0.06
    аниц
    -0.06
     invite
    -0.06
     essentially
    -0.06
    POSITIVE LOGITS
     COST
    0.07
    .setRequest
    0.07
    _FACE
    0.06
    备份
    0.06
    _MO
    0.06
     функ
    0.06
    .CODE
    0.06
    .cam
    0.06
    TEAM
    0.06
     stump
    0.06
    Act Density 0.100%

    No Known Activations