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

    Neuronpedia

    INDEX
    Explanations

    Explaining

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ocations
    -0.08
     htt
    -0.07
     드립니다
    -0.07
    Opened
    -0.07
    hões
    -0.06
     дозвол
    -0.06
     Shell
    -0.06
    /firebase
    -0.06
    ’ta
    -0.06
    ians
    -0.06
    POSITIVE LOGITS
     rem
    0.07
    	vec
    0.07
    َو
    0.07
    	GameObject
    0.06
     Freund
    0.06
    	Vec
    0.06
     Species
    0.06
     अपर
    0.06
     zví
    0.06
     Assumes
    0.06
    Act Density 0.003%

    No Known Activations