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

    Neuronpedia

    INDEX
    Explanations

    stretching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     attribution
    -0.07
     vocals
    -0.06
    adle
    -0.06
     Rails
    -0.06
    BracketAccess
    -0.06
     Cookies
    -0.06
    /access
    -0.06
     shows
    -0.06
     Adds
    -0.06
    _slave
    -0.06
    POSITIVE LOGITS
    .Tensor
    0.07
     своим
    0.07
     سان
    0.07
    0.07
    wiąz
    0.06
    ري
    0.06
    ��
    0.06
     sucked
    0.06
     për
    0.06
     lovely
    0.06
    Act Density 0.005%

    No Known Activations