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

    Neuronpedia

    INDEX
    Explanations

    tactics or misdirection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    collision
    -0.07
     airflow
    -0.06
     precedent
    -0.06
    	Simple
    -0.06
     ホ
    -0.06
    _CAM
    -0.06
     arrows
    -0.06
     enlarg
    -0.06
     Teachers
    -0.06
    vec
    -0.06
    POSITIVE LOGITS
     Charleston
    0.06
    �
    0.06
     istiyorum
    0.06
    {{--
    0.06
    019
    0.06
     wishing
    0.06
    άβ
    0.06
     ignite
    0.06
     displaced
    0.06
     Tang
    0.06
    Act Density 0.039%

    No Known Activations