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

    Neuronpedia

    INDEX
    Explanations

    was

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ��
    -0.07
     Bitcoin
    -0.07
     ET
    -0.07
    ge
    -0.06
     enclosed
    -0.06
     advertisers
    -0.06
    aming
    -0.06
    Descriptors
    -0.06
     diagnose
    -0.06
    _font
    -0.06
    POSITIVE LOGITS
    IsRequired
    0.06
     educate
    0.06
     پا
    0.06
     بعدی
    0.06
    幕
    0.06
    BOSE
    0.06
    効
    0.06
     предназнач
    0.06
    (Runtime
    0.05
    _playlist
    0.05
    Act Density 0.000%

    No Known Activations