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

    Neuronpedia

    INDEX
    Explanations

    c

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нельзя
    -0.07
     wealth
    -0.07
     safeguard
    -0.06
    izin
    -0.06
    	to
    -0.06
    ORTH
    -0.06
    .timestamp
    -0.06
    ている
    -0.06
    deliver
    -0.06
    _RESULT
    -0.06
    POSITIVE LOGITS
    考
    0.06
    Cow
    0.06
    �
    0.06
    ネ
    0.06
    mars
    0.06
    ành
    0.06
    аними
    0.06
     LES
    0.06
    rů
    0.06
    "]=>
    0.06
    Act Density 0.001%

    No Known Activations