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

    Neuronpedia

    INDEX
    Explanations

    argin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    служ
    -0.08
    (SELECT
    -0.07
     delighted
    -0.07
    Plug
    -0.07
     coc
    -0.07
    ульт
    -0.07
    三分
    -0.07
     Neptune
    -0.07
     admiration
    -0.07
    applicant
    -0.07
    POSITIVE LOGITS
     enorme
    0.07
     ');
    0.06
    });
    0.06
     deny
    0.06
    …I
    0.06
    悄
    0.06
    .Interop
    0.06
    �
    0.06
     GIR
    0.06
     Trim
    0.06
    Act Density 0.001%

    No Known Activations