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

    Neuronpedia

    INDEX
    Explanations

    personal thoughts and feelings

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pres
    -0.07
    くなります
    -0.07
    .mods
    -0.07
     Powerful
    -0.07
    .mag
    -0.07
     longing
    -0.06
     zwar
    -0.06
    庞
    -0.06
    .drag
    -0.06
     fixes
    -0.06
    POSITIVE LOGITS
    忞
    0.07
    	lbl
    0.07
    VICE
    0.07
    .fillStyle
    0.07
    Getty
    0.07
    贸易战
    0.07
     uniforms
    0.07
    استقلال
    0.07
     Confidential
    0.07
    铷
    0.06
    Act Density 0.069%

    No Known Activations