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

    Neuronpedia

    INDEX
    Explanations

    Vague, mixed contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bychom
    -0.07
     tob
    -0.06
    �
    -0.06
    etermine
    -0.06
     Raiders
    -0.06
    "]}↵
    -0.06
    .CONTENT
    -0.06
     }),↵
    -0.06
    �
    -0.06
     Jennifer
    -0.06
    POSITIVE LOGITS
    -defined
    0.08
    ��
    0.07
    cedes
    0.07
    ends
    0.07
    止
    0.07
     tram
    0.06
     馬
    0.06
     guidance
    0.06
    arah
    0.06
     connect
    0.06
    Act Density 0.000%

    No Known Activations