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

    Neuronpedia

    INDEX
    Explanations

    software vulnerabilities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     assault
    -0.09
    ORB
    -0.08
     assaults
    -0.08
     attacking
    -0.08
     attack
    -0.08
     Datenschutz
    -0.08
    	Vec
    -0.08
     attacker
    -0.08
     dét
    -0.08
     vlas
    -0.07
    POSITIVE LOGITS
     libraries
    0.08
    ибли
    0.08
    .strptime
    0.08
    ೊ
    0.08
     someplace
    0.08
     localidades
    0.07
     selectable
    0.07
     synthesis
    0.07
    libraries
    0.07
    інен
    0.07
    Act Density 0.004%

    No Known Activations