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

    Neuronpedia

    INDEX
    Explanations

    Blocking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Radio
    -0.06
    lectic
    -0.06
     Pull
    -0.06
     Wald
    -0.06
    gend
    -0.06
    Primitive
    -0.06
    Finish
    -0.06
     nal
    -0.06
    ΑΣ
    -0.06
     رد
    -0.06
    POSITIVE LOGITS
     تر
    0.08
    ころ
    0.06
    _DEF
    0.06
     blocking
    0.06
     pinterest
    0.06
    _logic
    0.06
     IRQ
    0.06
    urrence
    0.06
    �
    0.06
    .Checked
    0.06
    Act Density 0.001%

    No Known Activations