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

    Neuronpedia

    INDEX
    Explanations

    conversational elements, processes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     getting
    -1.59
    Getting
    -1.46
    getting
    -1.45
     Getting
    -1.38
     GETTING
    -1.30
     becoming
    -1.09
     gettin
    -1.06
    GETTING
    -1.05
    becoming
    -0.96
     gaining
    -0.94
    POSITIVE LOGITS
     Infórmanos
    0.75
    fted
    0.69
    WebVitals
    0.66
    aned
    0.66
    ly
    0.65
    ⓧ
    0.62
    0.60
    führt
    0.59
     rid
    0.58
    ered
    0.58
    Act Density 0.183%

    No Known Activations