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

    Neuronpedia

    INDEX
    Explanations

    nitrogen adsorption

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Он
    -0.07
    EHICLE
    -0.07
    ила
    -0.07
    Pri
    -0.07
    ربية
    -0.06
    nd
    -0.06
    utter
    -0.06
    ende
    -0.06
     перевір
    -0.06
     concerts
    -0.06
    POSITIVE LOGITS
     =========================================================================
    0.06
     eql
    0.06
     змі
    0.06
    �
    0.06
    /up
    0.06
     Getter
    0.06
    ‌شد
    0.06
    .AddScoped
    0.06
    =models
    0.05
    dq
    0.05
    Act Density 0.015%

    No Known Activations